GPT-Image-2.5 is now on Poe — both models.
Flare for fast, high-quality generation and rapid iteration. Sunburst for precise instruction following and detailed editing.
poe.com/GPT-Image-2.5-Flare
poe.com/GPT-Image-2.5-Sunburst
Poe (software)
-
Poe
@poe_platform
-
Poe
@poe_platform
GPT 6 Astra is now available on Poe! Try it out and see how it compares to other leading models and pushes the frontier of AI forward: poe.com/GPT-6-Astra
-
Poe
@poe_platform
Gemini-Omni-1.1-Flash is available on Poe.
@Google's multimodal video model — generate from text, images, or video; extend a scene; interpolate between first and last frames; edit in plain language.
Try it now → poe.com/Gemini-Omni-1.1-Flash -
Poe
@poe_platform
Claude Fable 5.1 is available on Poe.
@AnthropicAI's most capable model — built for demanding reasoning and long-horizon agentic work. 1M-token context, web search, adaptive thinking from low to max effort.
Try it now → poe.com/Claude-Fable-5.1 -
Poe
@poe_platform
Gemini 3.8 Flash is now available on Poe.
@Google's fast, cost-efficient workhorse for coding and agents — strong reasoning at Flash speed, with a 1M-token context window, web search, and adjustable thinking levels.
Try it now → poe.com/Gemini-3.8-Flash -
Poe
@poe_platform
Gemini 3.7 Flash is now available on Poe.
@GoogleAI's most intelligent workhorse model — fast, powerful reasoning for coding and agents, across a 1M-token context window for text, images, audio, and video.
Try it now → poe.com/Gemini-3.7-Flash -
Poe
@poe_platform
Grok 4.6 is now available on Poe.
@SpaceXAI's new frontier model — built for long-running agents, coding, and knowledge work, with a 500K-token context window.
Try it now → poe.com/Grok-4.6 -
Poe
@poe_platform
Try Claude Opus 5 on Poe.
@AnthropicAI's latest model is the most capable Opus model yet, approaching Claude Fable 5-level intelligence at half the price — with meaningful gains in agentic coding, knowledge work, visual understanding, and long-running tasks.
Try it today: -
Poe
@poe_platform
Gemini 3.6 Flash and Gemini 3.5 Flash-Lite from @GoogleDeepMind are available on Poe.
Gemini-3.6-Flash — Google's new workhorse model, with stronger coding, knowledge work, and multimodal performance, plus improved computer use
Gemini-3.5-Flash-Lite — the fastest model in the 3.5 series, built for high-volume, cost-efficient tasks and agentic workflows
Try them today:
poe.com/Gemini-3.6-Flash
poe.com/Gemini-3.5-Flash-Lite -
Poe
@poe_platform
The GPT-5.6 family from @OpenAI is now available on Poe: Sol, Terra, and Luna.
GPT-5.6-Sol — OpenAI's most capable model, built for complex reasoning, advanced coding, and agentic workflows.
GPT-5.6-Terra — balanced intelligence for everyday work, coding, analysis, and research.
GPT-5.6-Luna — fast, cost-efficient responses for high-volume and routine tasks.
Try them today:
poe.com/GPT-5.6-Sol
poe.com/GPT-5.6-Terra
poe.com/GPT-5.6-Luna -
Poe
@poe_platform
Introducing Temporary Chats on Poe
Temporary chats aren't saved to your chat history and don't use or update your Memory. Tap the Temporary Chat button in the top right of the Homepage or a new chat to try it.
Available now on web with Poe's official bots. -
Poe
@poe_platform
Grok 4.5 is now available on Poe.
@SpaceXAI's latest flagship brings sharper reasoning, stronger coding, and improved long-context handling for complex, multi-step work — built for agentic tasks and real-world problem solving.
Try it today: poe.com/grok-4.5 -
Poe
@poe_platform
Claude Fable 5 and Gemini Omni Flash are now on Poe!
Fable 5 is Anthropic's most powerful model, back to the public after a brief hiatus.
Gemini Omni Flash enables conversational video creation and editing — like Nano Banana, but for video — using world understanding for realistic motion and consistent edits.
Try them today:
poe.com/Claude-Fable-5
poe.com/Gemini-Omni-Flash -
Poe
@poe_platform
Sonnet 5 and Nano Banana 2 Lite are live on Poe.
Sonnet 5 is @AnthropicAI's most agentic model yet — Opus-level coding and reasoning at a fraction of the cost.
Nano Banana 2 Lite is @Google's fastest, most cost-effective image model — sharp, consistent images in ~4 seconds.
Try them today:
poe.com/Claude-Sonnet-5
poe.com/Nano-Banana-2-Lite -
Poe
@poe_platform
Kimi K2.7 Code and MiniMax M3 are now available on Poe. Two open-weight frontier models built for serious coding and agentic work.
Kimi K2.7 Code is Moonshot AI's strongest coding model yet, with smarter multi-step tool calling and 30% leaner reasoning.
MiniMax M3 pairs frontier agentic coding with a 1M-token context window and native image and video input.
Try them today:
poe.com/Kimi-K2.7-Code
poe.com/Minimax-M3-N -
Poe
@poe_platform
Claude Fable 5 is now available on Poe.
Anthropic's most capable model yet, built for long-running, complex work: large-scale code migrations, deep research, and agentic sessions that run for hours or days. State-of-the-art on nearly all tested benchmarks, with exceptional performance in coding, knowledge work, scientific research, and vision.
Try it today: poe.com/Claude-Fable-5 -
Poe
@poe_platform
Claude Opus 4.8 is now available on Poe.
Anthropic’s latest flagship model is built for enterprise-grade knowledge work, codebase-scale migrations, multi-agent coordination, and long-running autonomous tasks, with sharper judgment and improved honesty.
Try it today at: -
Poe
@poe_platform
Gemini-3.5-Flash is now available on Poe.
Google’s latest Flash model is built for fast, efficient responses, with strong performance on coding, complex workflows, and agentic tasks.
Try it today at: poe.com/Gemini-3.5-Flash -
Poe
@poe_platform
Memory is now available
Poe can remember your preferences, interests, and what you're working on across chats, so you don't have to repeat yourself. Works with most official bots, including Claude, GPT, and Gemini.
Off by default. Turn it on in Settings → Memory. -
Poe
@poe_platform
Grok 4.3 is now available on Poe.
It’s a great daily driver, not just a model that wins random benchmarks, but one that holds up for real-life use. It’s also economical enough to use every day, with strong performance for the price.
After sharing a lot of feedback with the @xai team, we’ve seen a big step up in how this new model handles complex tasks, especially those involving tool use.
Poe
@poe_platform
Check it out on all platforms at poe.com/Grok-4.3
-
Poe
@poe_platform
GPT-5.5 and GPT-5.5 Pro are live on Poe.
We’ve been testing it in early access across complex coding, debugging, and reasoning workflows.
On selected internal evals, we saw encouraging improvements:
- 12% higher task completion rate
- 16% fewer retries on complex prompts
- 19% better long-context performance
Poe
@poe_platform
Try them on all platforms and in the Poe API, available at: poe.com/GPT-5.5 and poe.com/GPT-5.5-Pro
-
Poe
@poe_platform
Claude Opus 4.7 is now available on Poe.
Anthropic's most capable model yet, with major improvements in coding, reasoning, long-context understanding, tool use, vision, and multi-step agent workflows.
You can try it in Poe app on all platforms and in the Poe API at
Poe
@poe_platform
What makes Opus 4.7 different: in our early testing it handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back. Designed for work you can hand off with less oversight.
Poe
@poe_platform
Under the hood: it has Extended Thinking Mode, optimized MCP support, multi-agent coordination, and a 1M-token context window. It works really well for workflows that need extensive planning, execution, and self-correction across different steps.
Poe
@poe_platform
Tip 1: Opus 4.7 uses a new tokenizer behind the scenes. In our testing, it can use between 1x and 1.5x more tokens when compared to Opus 4.6, so it’s worth planning accordingly.
Poe
@poe_platform
Tip 2: Opus 4.7 shows improvement on languages including those with less training data like Yoruba, Igbo and Chichewa. For folks who speak these and other languages this model will be meaningfully better.
Poe
@poe_platform
Tip 3: There is a big jump on coding tasks like
- SWE-Bench Pro 64.3%
- SWE-Bench Verified 87.6%
- TerminalBench 69.4%
Altogether, it’s a strong signal that coding performance has improved meaningfully in Opus 4.7 compared to Opus 4.6. -
Poe
@poe_platform
Gemini 3.1 Flash TTS is now available on Poe.
A fast, high-quality text-to-speech model from Google. A strong fit for voiceovers, audio content, accessibility features, and adding speech to agent workflows.
Try it in Poe app on all platforms and in the Poe API -
Poe
@poe_platform
Seedance 2.0 from ByteDance is now live on Poe.
Seedance 2.0 delivers high‑quality video generation across text and image inputs — built for cinematic scenes, consistent characters, and detailed motion control.
Seedance 2.0 Fast supports the same modes but is optimized for speed, making it ideal for rapid iteration, quick concept testing, and high‑volume creative workflows.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Seedance-2 and poe.com/Seedance-2-Fast -
Poe
@poe_platform
GLM‑5.1 by is now live on Poe.
z.ai’s flagship model for agentic engineering — delivering state‑of‑the‑art results on SWE‑Bench Pro and leading performance in repo generation and real‑world terminal tasks. A major step up from GLM‑5, with significantly stronger coding capabilities across the board.
Built for full repository generation, complex codebase refactoring, multi‑step terminal workflows, and autonomous, end‑to‑end engineering tasks.
Try it in the Poe app on all platforms and in the Poe API at poe.com/GLM-5.1-FW -
Poe
@poe_platform
Wan 2.7 is now live on Poe!
Four video generation modes in one model: Text-to-Video, Image-to-Video, Video Edit, and Reference-to-Video. Supports multi-shot generation, audio-driven output, first-and-last-frame control, and seamless video continuation -- from concept to final cut.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Wan-2.7 -
Poe
@poe_platform
Gemma 4 is now live on Poe.
Google's most capable open model: 31B dense parameters, 256K context window, 140+ languages, multimodal inputs, built-in chain-of-thought reasoning, and function calling support. Apache 2.0 licensed.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Gemma-4-31B -
Poe
@poe_platform
Qwen3.6 Plus is now live on Poe.
Delivers advanced vision‑language performance from Qwen, with clear gains in code‑heavy workflows like agentic and front‑end coding, plus stronger multimodal understanding including improved OCR and precise object localization.
Designed for developers who need reliable coding support alongside sharp visual reasoning in one model.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Qwen3.6-Plus -
Poe
@poe_platform
Poe now supports @opencode
An open-source AI coding terminal that pairs with all major models on Poe. One click login, instant access, no extra configuration.
Start building now.
poe.com/api/applications/OpenCode -
Poe
@poe_platform
Alibaba's Wan 2.7-Image is now live on Poe.
Generate a cohesive set of images from a single prompt with consistent characters, style, and context. Bounding box editing lets you refine specific regions without regenerating the whole image.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Wan2.7-Image -
Poe
@poe_platform
Yes, Kimi-K2.5-FW is free on Poe for a limited time only. No, this is not an April Fools' joke.
Poe
@poe_platform
Try it out on all platforms and in the Poe API today: poe.com/Kimi-K2.5-FW
-
Poe
@poe_platform
Veo 3.1 Lite is now live on Poe.
A lower-cost model in the Veo 3.1 family that generates video with native audio — including synchronized dialogue, sound effects, and ambient sound. Supports both text-to-video and image-to-video, with Veo 3.1's prompt adherence and scene understanding.
A strong fit for social clips, product demos, storyboards, short films, and rapid creative iteration.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Veo-3.1-Lite -
Poe
@poe_platform
Qwen3.5-Omni Plus and Qwen3.5-Omni Flash are now live on Poe.
Both models understand text, images, audio, and video. Plus handles up to 3 hours of audio and 1 hour of video per session, with audio input in 90+ languages and speech output in 30+ languages across 55 voice timbres.
Flash delivers the same cross-modal understanding at a lower cost — built for high-volume processing and multilingual voice workflows.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Qwen3.5-Omni-Plus and poe.com/Qwen3.5-Omni-Flash -
Poe
@poe_platform
MiniMax Speech 2.8 is now live on Poe.
A text-to-speech model with multiple voice presets, emotional tone control, and fine-grained audio settings. A strong fit for narrating videos, generating podcast voiceovers, building voice agents, or producing polished audio for apps and media.
Try it in the Poe app on all platforms and in the Poe API at poe.com/MiniMax-Speech-2.8 -
Poe
@poe_platform
Google DeepMind’s Lyria 3 is live on Poe!
Generate high‑fidelity music tracks up to three minutes long from text or image prompts — with control over vocals, genre, mood, and instrumentation. Great for scoring videos, prototyping song ideas, or turning a mood board into a fully produced track.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Lyria-3 -
Poe
@poe_platform
Xiaomi MiMo V2 models are live on Poe!
MiMo‑V2‑Flash - fast and cost‑efficient. Summarize documents, refactor code, batch‑process support tickets, generate structured outputs, and power high‑volume workflows where speed matters more than deep deliberation.
MiMo‑V2‑Omni - built for mixed media. Analyze product demo videos, pull details from screenshots, review voice recordings, and combine images + text into clear, actionable reports.
MiMo‑V2‑Pro - the heavy hitter. With up to 1M tokens of context, it can read massive codebases or long reports, plan multi‑step agent tasks, run deep research, and handle complex reasoning that requires long memory and structured thinking.
Poe
@poe_platform
You can try them now in Poe app on all platforms and in the Poe API at poe.com/MiMo-V2-Pro, poe.com/MiMo-V2-Omni, poe.com/MiMo-V2-Flash
-
Poe
@poe_platform
API Key Management is now available for the Poe API.
Create separate keys for tools like OpenClaw, Codex, Claude Code, Open WebUI, Cherry Studio, scripts, and more.
One account. Multiple keys. Cleaner workflow.
Manage keys: poe.com/api/keys
See supported apps: -
Poe
@poe_platform
MiniMax-M2.7 is live on Poe!
A next‑gen self‑evolving model built for autonomous software engineering and agent workflows. M2.7 can iteratively improve its own agent scaffolds, optimize task performance over repeated runs, and deliver major gains on real-world coding benchmarks like SWE-Pro. Great for multi-file codebase edits, long-horizon planning, tool use, document automation, and complex multi-agent tasks.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Minimax-M2.7 -
Poe
@poe_platform
Mistral Small 4 is live on Poe!
One model for reasoning, vision, and agentic coding. Good for things like solving multi-step math or research problems, extracting structured data from images or scanned documents, debugging and navigating a codebase, analyzing a chart and summarizing the takeaway, or parsing a dense PDF and pulling out what matters.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Mistral-Small-4 -
Poe
@poe_platform
OpenAI's GPT-5.4-Nano and GPT-5.4-Mini are now live on Poe.
GPT-5.4-Nano is a strong fit for fast, high-volume tasks like summarizing transcripts, labeling tickets, rewriting content, quick RAG answers, and running @openclaw flows with Poe where latency and cost matter most.
GPT-5.4-Mini is better for tasks like turning messy emails or notes into clean JSON, fixing a broken function without rewriting the whole file, deciding how to respond to an unusual support ticket, or carrying out an agent task that needs to plan, check results, and take a next step.
Try them today alongside every top model in the Poe app and API today at poe.com/GPT-5.4-Nano and poe.com/GPT-5.4-Mini. -
Poe
@poe_platform
Grok 4.20 Multi-Agent is live on Poe!
Instead of one model doing everything sequentially, @xai's new Grok 4.20 Multi-Agent spins up multiple specialized agents that search, analyze, and synthesize in parallel.
Ask it your hardest questions and watch as it spawns multiple agents in parallel server-side to produce a rigorously sourced answer with citations in minutes.
You can try it in the Poe app on all platforms and in the Poe API at poe.com/Grok-4.20-Multi-Agent -
Poe
@poe_platform
We had early access to GPT-5.4 and GPT-5.4 Pro, and they’re now available on Poe.
In our testing, the models were particularly strong at long workflows: debugging code, chaining tools together, and running deep research across many sources.
The big difference we noticed: persistence. They keep iterating on hard problems where earlier models often stop.
We also ran our own BrowseComp-style research eval and saw the same pattern—they were much better at “needle-in-a-haystack” queries that require digging across many pages and synthesizing the answer.
Combined with much longer context, they can track complex tasks without losing the thread.
GPT-5.4 is available at poe.com/GPT-5.4 and GPT-5.4-Pro at poe.com/GPT-5.4-Pro. Try them across all Poe platforms or via the Poe API. -
Poe
@poe_platform
GPT-5.3-Codex-Spark is now available on Poe in a limited research preview! Poe is one of the first places where this model is available today.
Enabled by Cerebras’s high-performance chips, OpenAI's newest lightweight coding model is optimized for ultra-fast code generation (~1000s tok/s) and supports a 128k context window.
Poe
@poe_platform
Try it alongside every top model in the Poe app and API today at poe.com/GPT-5.3-Codex-Spark. Pricing is 10 points/message to ensure broad access.
-
Poe
@poe_platform
GPT-5.3-Instant is live on Poe!
OpenAI's fastest GPT-5.3 model delivers near-instant responses while retaining strong reasoning and instruction-following. Built for high-throughput workflows where speed matters as much as quality.
You can try it in Poe app on all platforms and in the Poe API at poe.com/GPT-5.3-Instant -
Poe
@poe_platform
Gemini 3.1 Flash-Lite is live on Poe!
Gemini 3.1 Flash Lite is fast, cost-efficient lightweight reasoning model built for ultra-low latency workloads. Supports web search and up to 1 million tokens of input context, built for fast, scalable performance across real-time applications.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Gemini-3.1-Flash-Lite -
Poe
@poe_platform
Kling 3.0 family is live on Poe!
Kling 3.0 is a next-generation cinematic video model capable of creating up to 15-second narrative videos with multi-shot storyboarding, consistent characters and voices, physics-driven camera motion, and native audio. Kling O3 adds real-time optimization for faster, cost-efficient generation.
You can try them in Poe app on all platforms and in the Poe API at poe.com/Kling-v3, poe.com/Kling-v3-Pro, poe.com/Kling-O3 -
Poe
@poe_platform
Seed 2.0 mini is live on Poe!
ByteDance's latest model supports 256k context, image and video understanding, native web search, and four reasoning modes ranging from fast to deep. A strong option for developers who need flexible, cost-efficient reasoning.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Seed-2.0-Mini -
Poe
@poe_platform
Seedream 5.0 Lite is live on Poe!
A high-fidelity image generation model that integrates multi-step visual reasoning and precise control. Built with a unified multimodal architecture, it delivers superior character consistency, advanced editing capabilities, and enhanced world knowledge for production-level reliability across creative workflows.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Seedream-5.0-Lite -
Poe
@poe_platform
Qwen3.5 Flash is live on Poe!
A fast and efficient multimodal model that processes text and images seamlessly. Built with linear attention and a sparse mixture-of-experts architecture, it delivers improved inference efficiency and stronger performance than the 3 series across both text and vision tasks.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Qwen3.5-Flash -
Poe
@poe_platform
Nano Banana 2 is live on Poe!
Google’s latest image model combines Pro-level intelligence with lightning-fast generation. It features advanced world knowledge, precise text rendering, strong subject consistency, and 4K production-ready outputs.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Nano-Banana-2 -
Poe
@poe_platform
GPT-5.3-Codex is live on Poe!
OpenAI's most capable agentic coding model combines advanced reasoning with autonomous coding workflows. 25% faster than its predecessor, built for tasks you can start and walk away from.
Try it alongside every top model in the Poe app and API at -
Poe
@poe_platform
Gemini 3.1 Pro is live on Poe — Google’s newest Gemini model built to solve your hardest challenges: deep reasoning, synthesis, and complex problem solving. We got early access to a private snapshot and co-developed a custom benchmark to help shape this model with our partners at Google DeepMind.
Try it now in the Poe app on all platforms and in the Poe API: poe.com/Gemini-3.1-Pro -
Poe
@poe_platform
Claude Sonnet 4.6 is Anthropic’s latest model. It strikes a strong balance of quality, speed, and price for day-to-day work, with robust computer-use capabilities for tool-driven workflows and UI automation.
You can try the model in the Poe app on all platforms and in the Poe API at: poe.com/Claude-Sonnet-4.6 -
Poe
@poe_platform
Qwen3.5-Plus is live on Poe!
Qwen3.5‑Plus is a native vision‑language model built on a hybrid linear‑attention and sparse MoE architecture for greater inference efficiency. It features a 1M‑token context window, enabling powerful long‑context multimodal reasoning and agent workflows. Compared to Qwen3, it represents a major leap in both pure‑text and multimodal capabilities, performing on par with leading state‑of‑the‑art models.
You can try them in the Poe app on all platforms and in the Poe API at: poe.com/Qwen3.5-Plus -
Poe
@poe_platform
Minimax M2.5 is live on Poe!
The new Minimax M2.5 is designed for real world productivity, with a focus on planning‑driven, multi‑step execution across complex digital workflows. It excels at coding, cross‑tool context switching, and agent style task coordination. Also, it achieves strong results across real‑world coding and browsing benchmarks, and supports up to 205K token context window.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Minimax-M2.5 -
Poe
@poe_platform
GLM-5 is now available on Poe!
We found GLM-5 to be a big step up in coding during testing as part of our internal benchmarks. It shows improved long-horizon coherence and execution fidelity relative to prior open-weight models.
You can try it in Poe app on all platforms and in the Poe API at poe.com/GLM-5 -
Poe
@poe_platform
Opus 4.6 by @AnthropicAI just took the #1 spot on the leaderboard on Poe.
Strong signal that high-end reasoning, speed and real-world usability is winning right now.
poe.com/leaderboard -
Poe
@poe_platform
Claude Opus 4.6 is Anthropic’s most advanced model for professional work and long-running agents. It comes with big gains in reasoning, long-context, tool use, vision and coding.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Claude-Opus-4.6 -
Poe
@poe_platform
Grok Imagine is now available!
xAI’s Grok Imagine generates artistic images and cinematic short videos with audio support from text, image, or video. It is built for fast creative iteration, short‑form content, multiple variations per prompt, flexible aspect ratios, and expressive, stylized visuals. Also, both models let you edit existing image or video.
You can try it in Poe app on all platforms and in the Poe API today at: poe.com/Grok-Imagine-Image and poe.com/Grok-Imagine-Video. -
Poe
@poe_platform
Runway Gen‑4.5 is now on Poe!
Runway’s frontier video model generates cinematic, high‑fidelity video from natural language and images, offering fine‑grained control over motion, camera behavior, composition, and visual style.
You can try it in Poe app on all platforms and in the Poe API at poe.com/Runway-Gen-4.5 -
Poe
@poe_platform
Moonshot's latest open-weight model is now on Poe! It ranks #1 on @ArtificialAnlys's intelligence benchmark, supports visual reasoning and multi-step tool calls, at a competitive price.
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Kimi-K2.5 -
Poe
@poe_platform
New: GPT-5.2-Codex!
OpenAI's most advanced coding model is optimized for complex engineering tasks, recommended for long‑horizon, agentic coding workflows.
You can try it in the Poe app on all platforms and in the Poe API at poe.com/GPT-5.2-Codex. -
Poe
@poe_platform
You can now pin chats for quick, easy access to your favorite conversations.
To use this feature, go to your history on poe.com or in the desktop app and select more actions to pin any chat.
Support for Android and iOS is coming soon. -
Poe
@poe_platform
Now on Poe: MiniMax M2.1
An agent-optimized model built for coding, tool use, and long-horizon planning served via @novita_labs (1/2)
Poe
@poe_platform
Excels on SWE-bench (incl. multilingual), Terminal-bench, and long-horizon tasks.
Try it on Poe across web, desktop, mobile — and via the Poe API at poe.com/MiniMax-M2.1 (2/2) -
Poe
@poe_platform
Now on Poe: GLM-4.7
This next-generation foundation model, powered by @novita_labs on Poe, posts record‑breaking scores across several major reasoning and coding benchmarks. (1/2)
Poe
@poe_platform
You can try it in the Poe app on all platforms and in the Poe API at poe.com/GLM.4.7 (2/2)
-
Poe reposted
👩💻 Paige Bailey
@DynamicWebPaige
💸 One of the things that I'm (selfishly!) most excited about for reasoning models + native search is the ability to have a personalized Wirecutter, for anything.
Optimize for cost, color, walking distance proximity, time to get the product delivered, technical specs, and more: -
Poe
@poe_platform
Claude Code via the Poe API Live. We jump into using Claude Code with the new Anthropic Compatible API. x.com/i/broadcasts/1zqJVdaZmdAKB
-
Poe
@poe_platform
Gemini 3 Flash is on Poe!
This expansion to the Gemini 3 family delivers frontier intelligence with multimodal reasoning capabilities and speed for a fraction of the cost, making it one of the best models for everyday tasks. (1/2)
Poe
@poe_platform
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Gemini-3-Flash. (2/2)
-
Poe
@poe_platform
GPT-Image-1.5, the latest image generation model in ChatGPT, is live on Poe.
It offers exceptional prompt adherence, world knowledge, precise edits, and facial preservation with improved speed. (1/3)
Poe
@poe_platform
We are adding conversational image gen and editing support to the GPT 5 family of bots later today! (2/3)
Poe
@poe_platform
You can try it now on Poe at: poe.com/GPT-Image-1.5. (3/3)
-
Poe
@poe_platform
New: Anthropic API Compatibility. Use Claude Code with your Poe account to save up to 15% and have a single bill for all AI spend across providers.
You can learn more at: creator.poe.com/docs/external-applications/anthropic-comp…. -
Poe
@poe_platform
Gemini Deep Research is now on Poe! It is the best in the world on the DeepSearchQA benchmark, and provides autonomous, long‑running web research with fewer hallucinations, based on Gemini 3 Pro. (1/2)
Poe
@poe_platform
Be sure to give your entire research request in the initial prompt and include as much detail as you can. You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Gemini-Deep-Research. (2/2)
-
Poe
@poe_platform
The GPT 5.2 family is now on Poe!
The GPT‑5.2 family is OpenAI’s most advanced model for professional work and long‑running agents. It comes with big gains in reasoning, long‑context, tool use, vision, and coding. (1/2)
Poe
@poe_platform
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/GPT-5.2, poe.com/GPT-5.2-Chat, and poe.com/GPT-5.2-Pro. (2/2)
-
Poe
@poe_platform
Available now on Poe for everyone to try 👉 poe.com/goodreads-roaster
👩💻 Paige Bailey
@DynamicWebPaige
📚😂 I used the Poe scriptbot to build this (which it did, in one iteration!), but immediately regretted it. Hitting way too close to home:
And then there's the whiplash: You go from Numerical Recipes in C (because apparently you enjoy recreational suffering) straight to The Sea of Monsters. Nothing says "complex human being" like debugging algorithms in the morning and reading middle-grade Percy Jackson in the afternoon. I'm not judging the Percy Jackson—I'm judging that you have exactly ONE on this list, like you tried it, felt self-conscious, and ran back to the safety of Marcus Aurelius to feel smart again.
The funniest part? You read Freakonomics in 2005 and clearly thought "Yes, THIS is who I am now"—someone who reads pop economics and Nikola Tesla biographies while pretending Neverwhere counts as your fiction quota for the year. -
Poe
@poe_platform
GPT-5.1-Codex-Max is live on Poe!
OpenAI's most capable agentic coding model yet; released two weeks ago in the Codex CLI, now available to all; recommended for use in agentic harnesses or similar environments.
You can try it in the Poe app on all platforms and in the Poe API at poe.com/GPT-5.1-Codex-Max -
Poe
@poe_platform
Now on Poe: DeepSeek‑V3.2
This next-generation foundation model, powered by @novita_labs on Poe, is designed to unify high computational efficiency with state-of-the-art reasoning and agentic performance. (1/2)
Poe
@poe_platform
You can try it in the Poe app on all platforms and in the Poe API at poe.com/DeepSeek-V3.2. (2/2)
-
Poe
@poe_platform
Gemini 3 Pro saw instant adoption on Poe at launch, taking the top spot in subscriber usage among popular LLMs in its first week.
Check out our leaderboard for a real-time view of rankings on Poe at poe.com/leaderboard. -
Poe
@poe_platform
FLUX.2 Live on Poe with @fal x.com/i/broadcasts/1jMKgRdYXjYxL
-
Poe
@poe_platform
Flux.2 is live on Poe!
Black Forest Labs’ new state-of-the-art image model delivers sharp detail with strong style control and text rendering.
Powered by @fal on Poe, try it for concept art, product shots, and high-fidelity edits. (1/2)
Poe
@poe_platform
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/FLUX-2-Pro, poe.com/FLUX-2-Flex, and poe.com/FLUX-2-Dev. (2/2)
-
Poe
@poe_platform
Claude Opus 4.5 just landed on Poe!
It leads on 7 out of 8 programming languages on SWE-bench Multilingual and jumps 10.6% over Claude Sonnet 4.5 on Aider Polyglot.
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Claude-Opus-4.5. -
Poe
@poe_platform
Introducing script bots, a new way to combine models and automate workflows on Poe.
Script bots are created through vibe coding with Script Bot Creator and can combine any of the 200+ text, image, video, and audio models on Poe, plus any other bot on the platform. (1/9)Post not available here, view on X
Poe
@poe_platform
Script Bot Creator is initially available on web and desktop (mobile support soon). Any script bot will immediately work on all platforms and you can use them in group chats with up to 200 people. To read the full blog, visit: poe.com/blog/introducing-script-bots. (8/9)
Poe
@poe_platform
To showcase your bots, ask questions, and/or share feedback, join our Discord: discord.com/invite/joinpoe. We can’t wait to see what you create! (9/9)
-
Poe
@poe_platform
New! Nano Banana Pro is on Poe!
Nano Banana Pro (Gemini 3 Pro Image Preview) can make detailed, context-rich visuals, precisely edit or restyle input images with exceptional fidelity, and even generate legible text in images in multiple languages. (1/2)
Poe
@poe_platform
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Nano-Banana-Pro. (2/2)
-
Poe
@poe_platform
Now on Poe: Grok‑4.1‑Fast
This includes two models: Reasoning is best for agentic tool‑calling and Non‑Reasoning is a faster option for less complex tasks. Both support 2 million tokens of context (1/2)
SpaceX Super Intelligence
@SpaceXSI
Introducing Grok 4.1 Fast and the xAI Agent Tools API.
Grok 4.1 Fast is our best tool-calling model to date. With a 2M context window, it shines in real-world use cases like customer support and deep research.
x.ai/news/grok-4-1-fast
Poe
@poe_platform
You can try them in the Poe app on all platforms and in the Poe API at: poe.com/Grok-4.1-Fast-Reasoning and poe.com/Grok-4.1-Fast-Non-Reasoning (2/2)
-
Poe
@poe_platform
Gemini 3 Pro is now on Poe!
Benchmark results indicate it will offer state-of-the-art performance on math, coding, computer use, and long‑horizon agent tasks.
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Gemini-3.0-Pro. -
Poe
@poe_platform
Introducing group chat on Poe: a new way to collaborate with any AI and anyone you know, all in a single conversation.
Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)Post not available here, view on X
Poe
@poe_platform
A family or group of friends can plan a trip together using Gemini 2.5’s search functionality and o3 Deep Research. A team could work together to brainstorm images for mood boards using the many image models on Poe. (4/8)
Poe
@poe_platform
A group could play a trivia game mediated by a custom quiz bot like: poe.com/GuessTheFacts. The shared context means AI can moderate games, keep score, and create experiences that adapt to a group’s dynamics. (5/8)
Post not available here, view on X
Poe
@poe_platform
The team worked hard on this feature for many months, and we are going to keep improving it. Our support for all modalities, all AI providers, and all device platforms means we should be able to support many new use cases that are not currently possible on any product. (7/8)
Poe
@poe_platform
You can send feedback to feedback@poe.com and join our Discord to share use cases with other people exploring this new way of collaborating with AI. To read the full blog, visit: poe.com/blog/introducing-group-chat-for-all-poe-users (8/8)
-
Poe
@poe_platform
Four new OpenAI models are now on Poe: GPT-5.1-Instant, GPT-5.1, GPT-5.1-Codex, and GPT-5.1-Codex-Mini.
Instant is smart and more conversational, the full 5.1 model includes dynamic reasoning, and Codex models power coding via the Poe API. (1/2)
Poe
@poe_platform
You can try them in the Poe app on all platforms, in the Poe API, and at the following:
GPT-5.1-Instant → poe.com/GPT-5.1-Instant
GPT-5.1 → poe.com/GPT-5.1
GPT-5.1-Codex → poe.com/GPT-5.1-Codex
GPT-5.1-Codex-Mini → poe.com/GPT-5.1-Codex-Mini (2/2) -
Poe reposted
Adam D'Angelo
@adamdangelo
Quora's new mission is to grow the world's collective intelligence. This company-wide mission encompasses both the Quora product and Poe. More below on what this means to us:
-
Poe
@poe_platform
MiniMax-M2 is now available on Poe!
This open source model has a 200k token context window, has 230b parameters with an MoE architecture, and excels at coding and agent workflows. (1/2)
Poe
@poe_platform
You can try it at poe.com/Minimax-M2, across the Poe apps on all platforms, and via the Poe API. (2/2)
-
Poe
@poe_platform
Congrats to the @cartesia team and thanks for bringing Sonic-3 to Poe.
You can use it at poe.com/Cartesia-Sonic-3.0, on our apps, or with the Poe API, with full support for the model’s 100 new voices, 42 languages, and human-like expressiveness.
Karan Goel
@krandiash
We've raised $100M from Kleiner Perkins, Index Ventures, Lightspeed, and NVIDIA.
Today we're introducing Sonic-3 - the state-of-the-art model for realtime conversation.
What makes Sonic-3 great:
- Breakthrough naturalness - laughter and full emotional range
- Lightning fast -This media couldn't be displayed. See it on the original post. -
Poe
@poe_platform
We made a major upgrade to Poe App Creator, and it is now built on top of Claude Code. This update will generally produce significantly better results, especially when building and iterating on complex applications inside of Poe. (1/2)
Poe
@poe_platform
As usual, Poe apps you create with App Creator can build on top of any combination of the 200+ models on Poe. You can try the new experience at poe.com/App-Creator, and across the Poe iOS, Android, Mac, and Windows apps. (2/2)
-
Poe
@poe_platform
New: Poe Leaderboard
We launched a leaderboard that shows the most used AI models and apps across Poe's platform and API. Rankings are updated daily based on total token usage across the 200+ text, image, video, and audio bots on Poe. (1/2)
Poe
@poe_platform
To view the current rankings, go to poe.com/leaderboard (currently desktop and web only). (2/2)
-
Poe
@poe_platform
Now available: Claude Haiku 4.5!
Anthropic’s newest model balances intelligence and speed while delivering high performance in coding and agentic tasks. (1/2)
Poe
@poe_platform
Claude Haiku 4.5 is available at poe.com/Claude-Haiku-4.5, available across all platforms, and accessible through the Poe API. (2/2)
-
Poe
@poe_platform
Veo 3.1 and Veo 3.1 Fast are now on Poe.
The new release brings improvements to dialogue, sound effects, and overall video quality, which includes native 1080p resolution. Veo 3.1 Fast is optimized for quicker generation times and lower cost. (1/2)
Poe
@poe_platform
You can try Veo 3.1 at poe.com/Veo-3.1 and Veo 3.1 Fast at poe.com/Veo-3.1-Fast across all of our apps and in the Poe API. (2/2)
-
Poe
@poe_platform
The Poe API now supports tool calling for all OpenAI, Anthropic, and Google models. This means you can use the Poe API to power agentic workflows directly with code or in applications like @KiloCode, @roocode, @cline, @n8n_io, Codex CLI and more.
Poe
@poe_platform
Introducing the Poe API for developers, with three important features:
1) Access to all models and bots on Poe across all modalities
2) A standard OpenAI-compatible chat completions interface
3) The ability to purchase points beyond subscription limits 🧵 -
Poe
@poe_platform
Today we're adding transparent pricing to Poe. This means you can easily view USD costs for all models and compare our rates with other platforms. Models from Anthropic, Google, and OpenAI currently cost 10-30% less on Poe, with no hidden fees. (1/5)
Post not available here, view on X
Poe
@poe_platform
We hope this makes it straightforward to compare our offering directly to standard rates as you decide what platform best suits your needs. This is especially important for API users and people who benefit from high-usage and multi-model access in a single subscription. (4/5)
Poe
@poe_platform
We have more planned for the weeks and months ahead including new API tools, features, and integrations. You can get started with Poe today at poe.com.
We can't wait to see what you create! (5/5) -
Poe
@poe_platform
New on Poe: Sora 2 and Sora 2 Pro!
OpenAI’s new flagship video model generates hyper-realistic clips with synced audio and physical accuracy, allowing you to effortlessly turn text prompts into cinematic creations. (1/2)
Poe
@poe_platform
Sora 2 Pro produces longer, more complex scenes at higher resolution than base Sora 2.
Sora 2 Pro is available at poe.com/Sora-2-Pro, while Sora 2 is at poe.com/sora-2. You can try both across all platforms, and can be used through the Poe API. Enjoy! (2/2) -
Poe
@poe_platform
New: GPT-Image-1-Mini!
A faster and more cost-efficient version of OpenAI’s popular image gen model, it accepts both text and image inputs while creating high quality images with impressive instruction following, text rendering, and realism. (1/2)
Poe
@poe_platform
GPT-Image-1-Mini is available at poe.com/GPT-Image-1-Mini, across all platforms, and via the Poe API. (2/2)
-
Poe
@poe_platform
Now on Poe: GPT-5 Pro!
GPT-5 Pro is OpenAI’s most intelligent model ever. It’s great for assisting on complex tasks where you need high accuracy and depth of reasoning. (1/2)
Poe
@poe_platform
You can try GPT-5 Pro at poe.com/GPT-5-Pro, across all platforms, and through the Poe API. (2/2)
-
Poe reposted
EmpirioLabs AI
@empiriolabsai
We're happy to announce that the Amazon Nova family of bots from @awscloud has arrived on @poe_platform!
Amazon Nova delivers frontier intelligence across text, image, video, and agentic capabilities, giving you models tailored for different needs—from ultrafast text‑only performance to powerful multimodal video and image generation.
Some notable features include:
- Up to 2-minute video generation with Nova Reel 1.1
- Rich image generation & editing via Nova Canvas
- 1 million‑token context window in Nova Premier
- Support for multimodal inputs (text, image, video) with Nova Premier, Nova Pro & Nova Lite
Check out the demo video where we showcase the abilities of Nova Reel 1.1, Nova Canvas, and Nova Premier!
Try them out on Poe today:
Amazon-Nova-Reel-1.1 - poe.com/Amazon-Nova-Reel-1.1
Amazon-Nova-Canvas - poe.com/Amazon-Nova-Canvas
Nova-Premier-1.0 - poe.com/Nova-Premier-1.0
Nova-Pro-1.0 - poe.com/Nova-Pro-1.0
Nova-Lite-1.0 - poe.com/Nova-Lite-1.0
Nova-Micro-1.0 - poe.com/Nova-Micro-1.0This media couldn't be displayed. See it on the original post. -
Poe
@poe_platform
New: DeepSeek-V3.2-Exp!
@deepseek_ai’s new experimental model delivers strong performance for long-context queries.
You can try it at poe.com/DeepSeek-V3.2-Exp, in the Poe app across platforms, and use it in the Poe API. -
Poe
@poe_platform
Now on Poe: Claude Sonnet 4.5
@AnthropicAI’s most advanced model yet is one of the best in the world for complex tasks and excels in real-world coding. (1/2)
Poe
@poe_platform
You can try it at poe.com/Claude-Sonnet-4.5, in the Poe app across platforms, and use it in the Poe API. (2/2)
-
Poe
@poe_platform
New: You can now branch conversations from any message on Poe. Each branch copies the conversation up to that point into a new chat so you can test prompts, actions, or ideas and steer the direction without starting over. (1/2)
Poe
@poe_platform
Conversation branching is available today on web, MacOS, and Windows. You can access it within the follow-up actions of any message. (2/2)
-
Poe
@poe_platform
New Report: Our Summer 2025 analysis shows how recent Al model releases have impacted the landscape, revealing usage shifts across text, image, video, and audio.
Highlights: Growing momentum for Google, OpenAI’s GPT-5 launch, and rising global competition in multimedia gen. 🧵
Poe
@poe_platform
Google reshaped image generation in just one week.
Gemini-2.5-Flash-Image (aka Nano Banana) became an instant category leader, capturing +40% of all image gen usage just one week after its launch and demonstrating the market’s readiness for disruptive performance leaps. (2/6)
Poe
@poe_platform
Video generation is now a global competition.
Models from Chinese AI firms (Kling, Hailuo, Wan, and Seedance) now collectively capture over 50% of usage. Meanwhile, Google’s other viral sensation, Veo-3, secured 24% share with its breakthrough native audio generation. (3/6)Post not available here, view on X
Poe
@poe_platform
In audio, ElevenLabs defends its TTS lead (~74% share), with its new v3 model seeing swift adoption.
Music models also emerged on Poe this summer, with ElevenLabs Music taking an early 10.1% share of the audio category, ahead of Google's Lyria at 3.3%. (5/6)
Poe
@poe_platform
Our data provides a provider-agnostic look at the competitive dynamics shaping AI.
You can read the full Summer 2025 report on the Poe blog at poe.com/blog/report-summer-2025-ai-model-usage-trends and explore these models firsthand on poe.com. (6/6) -
Poe
@poe_platform
Now available on Poe: GPT-5-Codex!
This specialized version of GPT-5 is optimized for real-world dev tasks and agentic coding, with strong performance on benchmarks like SWE-bench for complex engineering workflows. (1/2)
Poe
@poe_platform
GPT-5-Codex is available at poe.com/GPT-5-Codex, across all platforms, and via the Poe API. (2/2)
-
Poe reposted
Ting Chen Liang
@ting_
Chat with the latest Deepseek V3.1-Terminus on
@poe_platform⚡️ Supported by us @novita_labs, and yes we are fast :Dd
✨ This model expands on V3.1's strengths:
> Cleaner language (fewer CN/EN mix-ups, no random chars)
> Upgraded Code Agent & Search Agent
Just built a model comparison chart with it, pretty slick 🤠 -
Poe
@poe_platform
Sonoma Alpha is the new Grok 4 Fast!
Grok 4 Fast is the latest frontier model from xAI, with multimodal reasoning and a 2M token context window. (1/2)
Poe
@poe_platform
Sonoma Alpha has arrived on Poe!
This highly intelligent, stealth model from a frontier US lab features a 2M token context window, image input, parallel tool support, and comes in reasoning (Sky) and non-reasoning (Dusk) versions. (1/2)
Poe
@poe_platform
You can try Grok 4 Fast with reasoning at poe.com/Grok-4-Fast-Reasoning, the non-reasoning version at poe.com/Grok-4-Fast-Non-Reasoning, and across all platforms.
Grok 4 Fast is also available through the Poe API. (2/2) -
Poe
@poe_platform
You can now share your private bots with other Poe users of your choosing.
To create a shareable link, open your bot’s Settings and change access to “Only people with access link.”
This feature keeps your bot unlisted while giving you more control over who has access. -
Poe
@poe_platform
Sonoma Alpha has arrived on Poe!
This highly intelligent, stealth model from a frontier US lab features a 2M token context window, image input, parallel tool support, and comes in reasoning (Sky) and non-reasoning (Dusk) versions. (1/2)
Poe
@poe_platform
Sonoma Alpha is free to use during this testing period, with anonymized prompts and outputs logged for the developer.
You can try Sonoma Sky at poe.com/Sonoma-Sky-Alpha, and Dusk at poe.com/Sonoma-Dusk-Alpha, across all platforms, and via the Poe API. (2/2) -
Poe reposted
Qwen
@Alibaba_Qwen
Excited to see Qwen3-Next-80B on Poe! 🚀
Poe
@poe_platform
New on Poe: Qwen3-Next-80B!
Alibaba’s latest model brings highly optimized inference → strong tokens/sec throughput + low latency, while still excelling on math & coding benchmarks. (1/2) -
Poe reposted
EmpirioLabs AI
@empiriolabsai
We're happy to announce that Stable-Audio-2.5 and Stable-Audio-2.0 from @StabilityAI are now available on @poe_platform!
Stable-Audio lets you generate audio up to 3 minutes long from text prompts. It supports text-to-audio, audio-to-audio transformations, and more, with customizable settings such as duration, steps, CFG scale, and others.
Check out the demo video (audio up!) below where the following prompt is used on Stable-Audio-2.5:
- Epic battle theme, choir, heavy drums, soaring brass
Try it out on Poe today:
Stable-Audio-2.5: poe.com/Stable-Audio-2.5
Stable-Audio-2.0: poe.com/Stable-Audio-2.0 -
Poe
@poe_platform
New on Poe: Qwen3-Next-80B!
Alibaba’s latest model brings highly optimized inference → strong tokens/sec throughput + low latency, while still excelling on math & coding benchmarks. (1/2)
Poe
@poe_platform
Qwen3-Next-80B is powered by @novita_labs. You can try it with thinking on/off at poe.com/Qwen3-Next-80B and poe.com/Qwen3-Next-80B-Think, across all platforms, and through the Poe API in your favorite coding apps. (2/2)
-
Poe reposted
Gareth Paul Jones 💙
@gpj
Released a new synthetic dataset: 1.5k [human] → 10k [synthetic] children’s stories.
Pipeline generated by @Kilo_Code and model switching from @poe_platform API 🙏🤗
huggingface.co/datasets/garethpaul/children-stories-dataset -
Poe
@poe_platform
The new Kimi K2 snapshot is here!
Kimi-K2-0905 brings a 256k context window (double the previous version), enhanced coding and math skills, and overall performance improvements. (1/2)
Poe
@poe_platform
You can try the latest Kimi K2 snapshot at poe.com/Kimi-K2-0905-T, across all platforms, and through the Poe API in your favorite coding apps. (2/2)
-
Poe
@poe_platform
Now on Poe: ElevenLabs Music!
This state-of-the-art music model lets you create custom tracks from a simple text prompt. You can describe the style, mood, and even the language to generate songs with lyrics or instrumentals. (1/2)
Poe
@poe_platform
You can also integrate this music bot into your own Poe Apps to create powerful new audio experiences.
ElevenLabs Music is available at poe.com/ElevenLabs-Music, across all platforms, and accessible through the Poe API. (2/2) -
Poe
@poe_platform
Gemini 2.5 Flash Image is dominating image generation on Poe right now.
In 72 hours it has captured 48% of image model messages, dethroning previous leaders Imagen-4-Ultra (27%→10%) and GPT-Image-1 (25%→13%). (1/2)
Poe
@poe_platform
You can try the new Gemini 2.5 Flash Image and any of the 100+ leading text, image, video, and audio models at poe.com, across platforms, and through our new Poe API. (2/2)
-
Poe
@poe_platform
Introducing the /compare command!
We’ve made it easier to see how different models respond to the same prompt in a single chat. After a response, just type /compare and @-mention any bot(s) in any chat on Poe.
Here’s an example comparing image editing across leading bots 🧵
Poe
@poe_platform
Prompt:
Add a banana rocket ship taking off into the sky in the distance. Change her shirt color to bright orange. Replace the background with an arctic environment with blue skies. Change her hair color to green. Replace the banana car with a strawberry car. (2/3)
Poe
@poe_platform
You can try it in chat today by typing /compare and @-mentioning any bot(s) you’d like after a response. (3/3)
-
Poe
@poe_platform
New on Poe: Grok Code Fast!
This high-performance, cost-efficient model from xAI is optimized for agentic coding applications. It offers visible reasoning traces, strong steerability, and supports a 256k context window. (1/2)
Poe
@poe_platform
Grok Code Fast is available through the Poe API on your favorite coding apps including RooCode, Cline, and KiloCode.
You can also try the bot at poe.com/Grok-Code-Fast-1 and across all platforms. (2/2) -
Poe
@poe_platform
Gemini 2.5 Flash Image is now available on Poe!
In our evaluation, this model delivers best-in-class image editing, combines images and styles seamlessly, and maintains top-tier consistency across multiple revisions. (1/3)
Poe
@poe_platform
Its precise editing and strong consistency make Gemini 2.5 Flash Image ideal for creating Poe Apps that let users modify or generate entirely new photos from a single source image. (2/3)
Poe
@poe_platform
You can try Gemini 2.5 Flash Image at poe.com/Gemini-2.5-Flash-Image and across all platforms. It is also available to use via the Poe API and as a base for prompt bots. (3/3)
-
Poe
@poe_platform
DeepSeek-V3.1 is now on Poe!
This highly anticipated model builds on top of DeepSeek-V3 and DeepSeek-R1 to support hybrid thinking mode, smarter tool calling, and improved thinking efficiency. (1/2)
Poe
@poe_platform
You can try DeepSeek-V3.1 at poe.com/DeepSeek-V3.1, powered by @FireworksAI_HQ. You can also use it as a base model for prompt bots and access it through the Poe API. (2/2)
-
Poe
@poe_platform
ElevenLabs v3 is now on Poe!
With new audio tags, multi-speaker support, and options for over 70 languages, this category leading model gives you more control to create audio that feels more real, natural and expressive. (1/2)
Poe
@poe_platform
ElevenLabs v3 is available through the “Speak” button below every bot response, as well as at poe.com/ElevenLabs-v3 and across all platforms. You can also use this model through our new API. (2/2)
-
Poe
@poe_platform
New usage data shows the launch of GPT-5 has marked a major upgrade cycle for our users. It climbed to number one in just 48 hours, growing to capture 33% of all subscriber messages on Poe within its first week. 🧵
Poe
@poe_platform
Among all LLMs to launch on Poe this year, this is the first time a model has passed GPT-4.1 since it took the lead last spring. Leading up to August 7, it held nearly 40% of all messages sent to top models among Poe subscribers. (2/3)
Poe
@poe_platform
You can try the new GPT-5 and any of the 100+ leading text, image, video, and audio models at poe.com and across platforms. You can also use any of these models through our new Poe API. (3/3)
-
Poe reposted
AK
@_akhaliq
For a limited time, GPT-5 is default in anycoder using @poe_platform
-
Poe
@poe_platform
Early data is showing GPT-5 is going to set a new record on Poe for week one usage.
Initial 24-hour usage data for GPT-5 reveals the model achieved a 37% share of all reasoning model messages on Poe, setting a new benchmark for models in its class. 🧵
Poe
@poe_platform
When viewed as a model family, this adoption is even more pronounced. The aggregated share of GPT-5 and its variants - mini (8%) and nano (5%) - accounts for 50% of the reasoning model usage across the platform over the past 24-hours. (2/5)
Poe
@poe_platform
Seeing a new model family capture 50% of category usage on day one is a powerful illustration of how quickly the landscape can shift. Our goal is to provide fast access to latest models across all modalities. (3/5)
Poe
@poe_platform
For developers using our API over the same 24-hour period, the GPT-5 family accounted for ~17% of total requests.
Usage was led by GPT-5-nano (8%), followed by mini (6%), and then GPT-5 (3%), showing a different adoption pattern than in chat. (4/5)
Poe
@poe_platform
While this is just a 24-hour snapshot, we will be monitoring how usage patterns shift throughout the week and will share an update on the trend. You can try these models through our API or directly:
poe.com/GPT-5
poe.com/GPT-5-mini
poe.com/GPT-5-nano. (5/5) -
Poe
@poe_platform
GPT-5 is here!
We’re excited to make OpenAI’s most advanced model ever available on Poe the morning of its release. It aims to set a new standard for speed, accuracy, and reliability. (1/2)
Poe
@poe_platform
You can try GPT-5 at poe.com/GPT-5, mini at poe.com/GPT-5-mini, and the nano version at poe.com/GPT-5-nano. You can also access these new models directly through our new API. (2/2)
-
Poe
@poe_platform
OpenAI's new gpt-oss is now on Poe!
gpt-oss-120b is a state-of-the-art open-source model that delivers exceptional performance in complex reasoning, multi-step problem-solving, and analysis. (1/2)
Poe
@poe_platform
Hosted by @TogetherCompute, you can try gpt-oss-120b at poe.com/GPT-OSS-120B-T and across all platforms. This model is also available via our new API. (2/2)
-
Poe reposted
Novita AI
@novita_labs
🔥 Novita AI’s models are now live on @poe_platform!
Try Qwen Image — our powerhouse text-to-image model.
✨ Highlights:
◆ SOTA text rendering: rivals GPT-4o for English, best-in-class for Chinese
◆ Crystal-clear in-image text: supports diverse fonts & styles (glowing, metallic, and more!)
Explore your creativity 👇 -
Poe
@poe_platform
Claude Opus 4.1 is now on Poe!
Anthropic’s best model for real-world coding and reasoning offers a clear upgrade in understanding and remembering context for more accurate, helpful conversations on your most complex topics. (1/2)
Poe
@poe_platform
Claude Opus 4.1 is available at poe.com/Claude-Opus-4-1 and across all platforms. You can also use this model in your favorite coding tools via our new API. (2/2)
-
Poe
@poe_platform
Several new specialized models are now available on Poe and through our API, including GLM-4.5, Wan 2.2, FLUX.1 Krea [dev], and Qwen3-Coder.
Here’s an overview of what each new model offers 🧵Post not available here, view on X
Poe
@poe_platform
Reka Research uses real-time web access to conduct deep research by synthesizing information from multiple sources, making it a useful model for academic, technical, or market research tasks. (poe.com/Reka-Research) (7/8)
Poe
@poe_platform
That's a quick look at our latest additions from this week. With these, you now have more bots on Poe for specialized tasks like video creation, in-depth research, and coding. Additionally, they are available for use through our newly released API. Enjoy! (8/8)
-
Poe
@poe_platform
Introducing the Poe API for developers, with three important features:
1) Access to all models and bots on Poe across all modalities
2) A standard OpenAI-compatible chat completions interface
3) The ability to purchase points beyond subscription limits 🧵Post not available here, view on X
Poe
@poe_platform
In addition to text models, you can access image models like Imagen 4 and FLUX Kontext, video models including Veo 3 and Hailuo 02, and audio models like ElevenLabs and Lyria. This can be valuable for media generation workflows that chain models together across modalities. (4/7)
Poe
@poe_platform
If your subscription points aren't enough, you can now purchase additional points at cost. These points work seamlessly across both our API and Poe chat. (5/7)
Poe
@poe_platform
This launch is just the start. We'll be adding new capabilities based on developer feedback in the coming weeks and months. (6/7)
Poe
@poe_platform
To get started, you can generate an API key at poe.com/api_key, read the docs at creator.poe.com/docs/api, and send feedback and requests to developers@poe.com. We’re excited to see what you build! (7/7)
-
Poe
@poe_platform
Now on Poe: Qwen3-235B-2507!
The latest Qwen3-235B snapshot shines with top-tier benchmarks, improved performance on reasoning and knowledge tasks, and a large 256k-token context window. (1/2)
Poe
@poe_platform
You can try Qwen3-235B-2507-FW at poe.com/Qwen3-235B-2507-FW and in the Poe app across all platforms. (2/2)
-
Poe
@poe_platform
We’ve upgraded our GPT Image bots following OpenAI’s high input fidelity release to the API.
Now you can make precise edits while preserving fine details and character consistency. (1/2)
Poe
@poe_platform
You can try the upgraded image editing in GPT-4o at poe.com/GPT-4o and across iOS, Android, Mac and Windows. Enjoy! (2/2)
-
Poe
@poe_platform
Grok 4's adoption slope on Poe is one of the steepest we've seen among reasoning models in the days following launch. It only took three days to beat the previous week-one record holder, o3. (1/2)
Poe
@poe_platform
You can try Grok 4 now at poe.com/Grok-4, explore all leading reasoning models at poe.com/explore?category=Reasoning, and across all platforms. (2/2)
-
Poe
@poe_platform
Now on Poe: Kimi K2!
Kimi K2 ranks as a top open-source model (SWE-bench Verified at 65.8%), excelling at coding and solving technical problems. (1/2)
Poe
@poe_platform
Hosted on Poe by @FireworksAI_HQ, you can try Kimi K2 at poe.com/Kimi-K2-Instruct and across all platforms. (2/2)
-
Poe
@poe_platform
Grok 4 is now on Poe!
It sets new performance records across nearly all benchmarks and has taken the lead among the frontier models. (1/2)
Poe
@poe_platform
Grok 4 is available now at poe.com/Grok-4 and on the Poe app across iOS, Android, Mac, and Windows. (2/2)
-
Poe
@poe_platform
Hailuo 02 is now on Poe!
This new video model stands out for its ability to handle real-world physics and motion where other leading-edge models struggle. It supports text and image prompts, and generates videos that are 6 seconds long. (1/2)
Poe
@poe_platform
You can start creating videos with Hailuo 02 at poe.com/Hailuo-02 and across all platforms. (2/2)
-
Poe
@poe_platform
New: o3-deep-research and o4-mini-deep-research!
We're excited to bring OpenAI's deep research models to Poe. Now you can tackle complex research tasks and then switch to other models for writing, coding, and media generation all in one chat. (1/3)
Poe
@poe_platform
Both models can also pull external context through web search. We suggest starting with o4-mini-deep-research first. If you aren't happy with the result, switch to o3-deep-research. (2/3)
Poe
@poe_platform
You can use o4-mini-deep-research at poe.com/o4-mini-deep-research and o3-deep-research at poe.com/o3-deep-research, and in the Poe app across platforms. (3/3)
-
Poe
@poe_platform
New on Poe: Phoenix 1.0!
This image model from Leonardo AI supports prompts up to 1500 characters, features an optional prompt enhancer to optimize complex instructions, and has 25 different style presents, including Macro, Sketch, and 3D Render. (1/2)
Poe
@poe_platform
Phoenix 1.0 is available at poe.com/Phoenix-1.0 and on iOS, Android, Mac, and Windows. Enjoy! (2/2)
-
Poe
@poe_platform
New on Poe: Lyria!
Google DeepMind’s music-gen model creates high-fidelity instrumental tracks directly from your text prompts. With detailed control over style, instruments, and tempo, you can transform your creative ideas into music right from chat. (1/2)
Poe
@poe_platform
As the first music generation model on Poe, you can also now build custom experiences around Lyria with Poe Apps.
Lyria is available for you to try at poe.com/Lyria and across all platforms.
We’re excited to see what you create with it! (2/2) -
Poe
@poe_platform
New: Seedream 3.0 & Seedance 1.0 Lite!
Seedream 3.0 creates crisp, vibrant images, while Seedance 1.0 Lite quickly generates stunning videos with realistic motion.
On Poe, you can create images with Seedream, then @-mention Seedance to turn them into videos in one chat. (1/2)
Poe
@poe_platform
You can try Seedream 3.0 at poe.com/Seedream-3.0, Seedance 1.0 Lite at poe.com/Seedance-1.0-Lite, and on across all platforms. (2/2)
-
Poe
@poe_platform
With FLUX Kontext Pro and GPT-Image-1, you can make conversational edits to images while preserving the subject. This includes use cases like altering appearances, adding objects, and/or replacing backgrounds.
Here are a few examples comparing the two models on Poe 🧵Post not available here, view on X
Poe
@poe_platform
“Change her hair color to purple and replace her bag with a yellow umbrella”. (5/6)
Poe
@poe_platform
You can try FLUX Kontext Pro at poe.com/Flux-Kontext-Pro, GPT-Image-1 within poe.com/GPT-4o, and on all Poe apps across platforms. (6/6)
-
Poe
@poe_platform
o3-pro is now on Poe!
OpenAI’s o3-pro is its smartest model to date, outshining o3 and o1-pro in math, science, and coding. It features a 200k token context window and excels at complex, multi-step reasoning. (1/2)
Poe
@poe_platform
You can compare o3-pro with other top models in chat to see how it stacks up.
o3-pro is available at poe.com/o3-pro and across all platforms. Enjoy! (2/2) -
Poe
@poe_platform
o3 is now 80% cheaper on Poe!
Sam Altman
@sama
we dropped the price of o3 by 80%!!
excited to see what people will do with it now.
think you'll also be happy with o3-pro pricing for the performance :)
Poe
@poe_platform
You can try it at poe.com/o3 and across all platforms.
-
Poe
@poe_platform
New: Retro Diffusion Plus!
Specializing in high-quality pixel art, this upgraded model offers 11 new styles, improved prompt accuracy, and enhanced image clarity.
You can choose any style or customization options using the ‘Additional input’ button below the chat. (1/2)
Poe
@poe_platform
Retro Diffusion Plus is available at poe.com/Retro-Diffusion-Core, and across all platforms. (2/2)
-
Poe
@poe_platform
Now on Poe: Gemini 2.5 Pro just got an upgrade that is crushing benchmarks (SOTA on HLE, Aider, GPQA, and more).
Key improvements include enhanced multi-turn conversation abilities, complex reasoning, sophisticated coding, and creative writing. (1/2)
Poe
@poe_platform
You can try it at poe.com/Gemini-2.5-Pro-Preview and across all platforms. (2/2)
-
Poe
@poe_platform
Since launching Kling 2.1 Pro on Poe a few days ago, we’ve been impressed with its ability to transform images into stunning 1080p videos.
You can combine it with image models on Poe to generate videos in a single chat like this example using FLUX Kontext. (1/3)
Poe
@poe_platform
Here’s a comparison of Kling 2.1 Pro and Kling v1.6 that produced improvements in quality and clarity when using this image-to-video prompt: The camera stays in place as a dinosaur emerges from the forest. The dinosaur looks around, then runs off. (2/3)
Poe
@poe_platform
You can find Kling 2.1 Pro at poe.com/Kling-2.1-Pro and across all platforms. We look forward to seeing what you create! (3/3)
-
Poe
@poe_platform
New on Poe: FLUX Kontext!
Its multi-turn editing lets you refine images quickly with text prompts using our “Remix” button - allowing you to preserve character consistency while editing and even restyling your images. (1/3)
Poe
@poe_platform
The new FLUX Kontext family features two versions: Pro and Max.
Pro is great for fast, step-by-step editing, keeping people and styles consistent.
Max delivers sharper details and better text rendering for higher-quality generations. (2/3)
Poe
@poe_platform
You can try FLUX Kontext Pro at poe.com/Flux-Kontext-Pro, Max at poe.com/Flux-Kontext-Max, and across all platforms. (3/3)
-
Poe
@poe_platform
Now on Poe: Veo 3!
Veo 3 sets a new standard as the most advanced video model yet, producing highly realistic visuals and immersive audio from text and image-based prompts. (1/2)
Poe
@poe_platform
Veo 3 is available at poe.com/Veo-3 and across all platforms, allowing you to generate videos from your phone. Enjoy!
-
Poe
@poe_platform
New: Runway Gen-4 Turbo!
Runway’s latest video model lets you generate dynamic, high-quality videos with realistic motion from text or images with impressive speed. (1/3)
Poe
@poe_platform
We’ve also upgraded the “Animate” button to Gen-4 Turbo, making it easier for you to bring any image you generate to life with just one click. (2/3)
Poe
@poe_platform
Runway Gen-4 Turbo is available at poe.com/Runway-Gen-4-Turbo and on all platforms. (3/3)
-
Poe
@poe_platform
Now on Poe: Imagen 4!
Imagen 4 is the newest text-to-image model from Google DeepMind. It produces realistic images with sharpened clarity and impressive speed. (1/2)
Poe
@poe_platform
Imagen 4 is available at poe.com/Imagen-4 and across all platforms. (2/2)
-
Poe
@poe_platform
Claude Opus 4 and Sonnet 4 are now available on Poe!
Claude Opus 4 is Anthropic’s most advanced model ever, delivering top-tier performance for coding and complex tasks. (1/3)
Poe
@poe_platform
Claude Sonnet 4 improves on its predecessor with strengthened coding and instruction-following, and is designed to handle both everyday and complex tasks.
Both Claude Opus 4 and Sonnet 4 are hybrid reasoning models with adjustable thinking budgets. (2/3)
Poe
@poe_platform
You can try Claude Opus 4 at poe.com/Claude-Opus-4, Claude Sonnet 4 at poe.com/Claude-Sonnet-4, and across all platforms. Enjoy! (3/3)
-
Poe
@poe_platform
The world’s fastest inference for Llama 4 Scout is now on Poe!
At over 2,600 tokens per second, this bot allows for near-instant interactions. (1/2)
Poe
@poe_platform
You can try Cerebras’ Llama 4 Scout Nitro at poe.com/Llama-4-Scout-nitro and on all platforms. (2/2)
-
Poe reposted
Inception
@_inception_ai
We're live on @poe_platform!
Poe users can start interacting with Mercury Coder Small immediately through the chat interface. And developers and builders looking to integrate a dLLM into their own tools or platforms can access it via the Poe API.
poe.com/Mercury-Coder-Small -
Poe
@poe_platform
New report: How have 2025’s breakthrough model launches influenced AI usage patterns?
Our latest ecosystem report examines demand and share-of-usage based on millions of interactions on Poe across text, image, video, audio, and reasoning models. Key highlights: 🧵Post not available here, view on X
Poe
@poe_platform
Image generation is becoming increasingly competitive as quality and adherence improve.
OpenAI's GPT-Image-1 rapidly grew to 17% of usage in the two weeks after its API launch, mirroring the viral success in the ChatGPT app in March. (3/5)
Poe
@poe_platform
Kling 2.0 emerged as a top contender in video generation in just three weeks.
Kuaishou's Kling family has rapidly grown to ~30% of usage as its newest model, Kling 2.0, has risen to over 20% in just three weeks. (4/5)
Poe
@poe_platform
This data offers a provider-agnostic perspective on the dynamic AI model landscape. We invite you to review the full report on the Poe blog (poe.com/blog/spring-2025-ai-model-usage-trends) and to explore these models firsthand on poe.com. (5/5)
-
Poe
@poe_platform
Gemini 2.5 Pro on Poe has been updated to the new I/O edition from Google DeepMind!
This upgrade delivers significantly improved coding abilities and performance, especially for tasks related to web development. (1/2)
Poe
@poe_platform
Now on Poe: Gemini 2.5 Pro!
This is the most powerful model in the world today according to a few benchmarks, and it is #1 ranked on LMArena by a large margin. It supports text, image, video, and audio input, and has a 1M token context window. (1/2)
Poe
@poe_platform
You can try the upgraded Gemini 2.5 Pro at poe.com/Gemini-2.5-Pro-Exp and on all platforms. (2/2)
-
Poe
@poe_platform
New on Poe: Kling 2.0!
This advanced video model sets new standards for motion quality and image-to-video capabilities. It excels at transforming images you create on Poe, including those generated with GPT-4o, into high-quality videos. (1/2)
Poe
@poe_platform
Kling 2.0 is hosted by @FAL and is available at poe.com/Kling-2.0-Master and on all platforms. (2/2)
-
Poe
@poe_platform
New: Gemini 2.5 Flash!
Google DeepMind's latest model has hybrid reasoning capabilities, along with a 1m token context window, multimodal input support, and native search, all while prioritizing speed and cost. (1/2)
Poe
@poe_platform
You can try Gemini 2.5 Flash at poe.com/Gemini-2.5-Flash-Preview and on all platforms. (2/2)
-
Poe
@poe_platform
✅
-
Poe reposted
Adam D'Angelo
@adamdangelo
I really enjoyed this conversation with Rick Rubin. We talked about the early days of Facebook, Quora, Poe, AGI, user-generated content, and vibe coding. Link in next tweet.
-
Poe
@poe_platform
Now on Poe: Qwen3!
This powerful new model from Alibaba combines reasoning and performance to excel at complex tasks. (1/3)
Poe
@poe_platform
Qwen3's hybrid reasoning system lets you switch between quick answers and thorough problem-solving. Use --no_think for rapid responses or --think for detailed reasoning (enabled by default). (2/3)
Poe
@poe_platform
You can try Qwen3-235B-A22B at poe.com/Qwen3-235B-A22B-FW and across all platforms. (3/3)
-
Poe
@poe_platform
GPT image generation is on Poe! It pushes the boundaries of image quality and prompt adherence.
Unique to Poe, you can generate many versions at once with the repeat command, send requests while an image generates, and combine it with any other model. (1/3)
Poe
@poe_platform
It excels at following prompts, rendering text, and transforming uploads into any style. You can use it to create image-based apps with App Creator and/or pair it with video models like Kling or Veo 2. (2/3)
Poe
@poe_platform
You can try it at GPT-4o at poe.com/GPT-4o and across all platforms. Prompt and server bot creators can use it as a base model too with the standalone GPT-Image-1 bot. (3/3)
-
Poe
@poe_platform
Now available: Grok 3 and Grok 3 Mini!
Grok 3 is xAI's flagship model with deep expertise across specialized domains. It gives in-depth answers to complex queries, drawing on its extensive knowledge across specialized fields. (1/3)
Poe
@poe_platform
Grok 3 Mini offers lightweight reasoning capabilities and excels at clear, concise reasoning for everyday questions and logical problems. It’s designed for straightforward interactions where extensive expertise isn't needed. (2/3)
Poe
@poe_platform
You can try Grok 3 at poe.com/Grok-3, Grok 3 Mini at poe.com/Grok-3-Mini, and on all platforms. (3/3)
-
Poe
@poe_platform
o3 and o4-mini are now on Poe!
OpenAI's smartest models yet - o3 is designed to take on the most complex problems and offers extensive visual analysis capabilities, while o4‑mini combines reasoning and speed to excel at everyday tasks. (1/2)
Poe
@poe_platform
You can try o3 at poe.com/o3, o4-mini at poe.com/o4-mini, and on all platforms Poe is available. (2/2)
-
Poe
@poe_platform
Now on Poe: GPT-4.1, mini, and nano!
GPT-4.1 is OpenAI’s new flagship model with significantly improved coding skills, long context (1M tokens), and improved instruction following. (1/3)
Poe
@poe_platform
GPT-4.1 mini is smaller, faster, and matches or beats GPT-4o in intelligence and vision-related tasks.
Rounding out the new bots, GPT-4.1 nano stands as their fastest and cheapest model yet, with the ability to handle 1M tokens as well. (2/3)
Poe
@poe_platform
You can try GPT-4.1 (poe.com/GPT-4.1), mini (poe.com/GPT-4.1-mini), and nano (poe.com/GPT-4.1-nano) on web and across all platforms. (3/3)
-
Poe
@poe_platform
New: Gemini 2.0 Flash native image generation!
This bot supports image output and conversational editing, allowing you to create and refine images by describing what you want. (1/3)
Poe
@poe_platform
You can also generate text and images together in one request. For example, it can create a short story about a topic while generating images for each scene based on your direction. (2/3)
Poe
@poe_platform
Native image generation is available in Gemini 2.0 Flash Experimental at poe.com/Gemini-2.0-Flash-Exp and on all platforms where Poe is available. (3/3)
-
Poe
@poe_platform
Now on Poe: Kling Pro v1.6!
This model ranks among the best image-to-video generators available. It works especially well with our state-of-the-art image generation bots, turning pictures into dynamic scenes with smooth, consistent motion. (1/2)
Poe
@poe_platform
You can create videos with Kling Pro v1.6 via text and image inputs at poe.com/Kling-Pro-v1.6, and across all platforms where Poe is available. (2/2)
-
Poe
@poe_platform
The first versions of Llama 4 Scout and Maverick are now available on Poe, thanks to @FireworksAI_HQ!
AI at Meta
@AIatMeta
Today is the start of a new era of natively multimodal AI innovation.
Today, we’re introducing the first Llama 4 models: Llama 4 Scout and Llama 4 Maverick — our most advanced models yet and the best in their class for multimodality.
Llama 4 Scout
• 17B-active-parameter model with 16 experts.
• Industry-leading context window of 10M tokens.
• Outperforms Gemma 3, Gemini 2.0 Flash-Lite and Mistral 3.1 across a broad range of widely accepted benchmarks.
Llama 4 Maverick
• 17B-active-parameter model with 128 experts.
• Best-in-class image grounding with the ability to align user prompts with relevant visual concepts and anchor model responses to regions in the image.
• Outperforms GPT-4o and Gemini 2.0 Flash across a broad range of widely accepted benchmarks.
• Achieves comparable results to DeepSeek v3 on reasoning and coding — at half the active parameters.
• Unparalleled performance-to-cost ratio with a chat version scoring ELO of 1417 on LMArena.
These models are our best yet thanks to distillation from Llama 4 Behemoth, our most powerful model yet. Llama 4 Behemoth is still in training and is currently seeing results that outperform GPT-4.5, Claude Sonnet 3.7, and Gemini 2.0 Pro on STEM-focused benchmarks. We’re excited to share more details about it even while it’s still in flight.
Read more about the first Llama 4 models, including training and benchmarks ➡️ go.fb.me/gmjohs
Download Llama 4 ➡️ go.fb.me/bwwhe9
Poe
@poe_platform
You can access them at poe.com/Llama-4-Scout and poe.com/Llama-4-Maverick and on Poe apps across all platforms. Enjoy!
Poe
@poe_platform
And you can now access the Together versions of these models, at poe.com/Llama-4-Scout-T and poe.com/Llama-4-Maverick-T !
-
Poe
@poe_platform
Now on Poe: Gemini 2.5 Pro!
This is the most powerful model in the world today according to a few benchmarks, and it is #1 ranked on LMArena by a large margin. It supports text, image, video, and audio input, and has a 1M token context window. (1/2)
Poe
@poe_platform
Gemini 2.5 Pro is available at poe.com/Gemini-2.5-Pro-Exp and on Poe apps across all platforms. (2/2)
Poe
@poe_platform
Rate limits have been updated! Thank you to @OfficialLoganK and @GoogleDeepMind.
-
Poe
@poe_platform
Now available: Retro Diffusion Core!
This specialized image model creates professional-grade pixel art across across 15 style presets, including anime, game assets, and even animation frames. (1/3)
Poe
@poe_platform
You can customize dimensions, use seeds for consistency, create tileable textures, and also generate ‘walking’ animations. The bot maintains proper pixel structure at any resolution, making it great for games and animations. (2/3)
Poe
@poe_platform
You can try Retro Diffusion Core at poe.com/Retro-Diffusion-Core and across all platforms. Enjoy! (3/3)
-
Poe reposted
Baseten
@baseten
The first Baseten bot is live on Poe! It's very fast, you can ask questions in your language of choice and get instant answers.
We're excited to partner with Quora to power the fastest open-source models for the Poe community! -
Poe
@poe_platform
By popular demand, we are introducing two new subscription options today, at $5/month and $250/month. These align Poe with two simultaneous trends in AI: normal models are getting cheaper and the most advanced models are getting more expensive. (1/5)
Post not available here, view on X
Poe
@poe_platform
Across all our subscription tiers, we aim to have the lowest effective price for any particular model. If you'd like to try either of them, visit poe.com through the web or mobile web, and click "Subscribe" or "Upgrade" in the sidebar. (4/5)
Poe
@poe_platform
Your feedback was very important to the creation of these new options, and we're excited to see how you use them. You can try Poe today at poe.com and across our iOS, Android, Mac, and Windows apps. (5/5)
-
Poe
@poe_platform
The latest version of DeepSeek V3 is now available!
Today’s update improves its math, coding, and general reasoning performance, making it one of the most powerful open-source LLMs available. (1/2)
Poe
@poe_platform
You can try the new DeepSeek V3 (hosted by @FireworksAI_HQ) at poe.com/Deepseek-V3-FW and on all platforms. (2/2)
-
Poe
@poe_platform
We've added a few highly-requested features on Poe this week, including follow-up actions for all messages, easier undo for context clear, and one-click chat sharing for your entire chat. Details below 🧵
Post not available here, view on X
Poe
@poe_platform
We've also made it easier to restore your conversation after clearing the context. With the new "Undo" button, you can revert your chat to its previous state. (3/4)
Poe
@poe_platform
Finally, we’ve made it easier for you share your entire chat with one click. For more granular sharing, you can still choose specific messages to share. (4/4)
-
Poe
@poe_platform
Now on Poe: o1 pro!
OpenAI’s o1 pro is among the most powerful reasoning models available. It’s tailored for complex, compute-heavy tasks, dedicating additional thinking time to deliver more accurate, reliable answers. (1/2)
Poe
@poe_platform
You can try o1 pro at poe.com/o1-pro, and across all platforms. (2/2)
-
Poe
@poe_platform
Now on Poe: GPT-4o and GPT-4o Mini with search! These bots can access the web to provide you with more informed answers based on real-time data. (1/2)
Poe
@poe_platform
You can try GPT-4o-Search at poe.com/GPT-4o-Search, and GPT-4o-Mini-Search at poe.com/GPT-4o-Mini-Search, and across all platforms. (2/2)
-
Poe
@poe_platform
New Report: How has AI usage changed over the last year? Our analysis of model usage on Poe provides insights around user preferences, adoption rate, and disruptions. Key highlights from our Early 2025 AI Ecosystem Trends report: 🧵
Poe
@poe_platform
Anthropic usage surged in 2024. Since Claude 3.5 Sonnet’s June 2024 launch, OpenAI and Anthropic models have shared nearly equal usage, highlighting growing competition among text-based LLMs. (2/6)
Post not available here, view on X
Poe
@poe_platform
In video, despite some decline in usage share over time and only offering a single model in their API since its launch in September 2024, Runway has maintained a strong position with 30-50% of video gen messages, but with Google’s Veo-2 now rising fast. (5/6)
Poe
@poe_platform
For those interested in additional insights and the details behind these observations, you can find more information at: poe.com/blog/report-early-2025-ai-ecosystem-trends. (6/6)
-
Poe reposted
Cohere Labs
@Cohere_Labs
Our state-of-the-art multilingual, multimodal model, Aya Vision, is available on @poe_platform 🔥
Thanks to the entire Poe team for partnering on this launch, particularly @nhuber, Aaron Gamble, John Li, @KevinOlivieri, Marcie Peters, and @adamdangelo.
poe.com/Aya-Vision
Cohere Labs
@Cohere_Labs
Introducing ✨ Aya Vision ✨ - an open-weights model to connect our world through language and vision
Aya Vision adds breakthrough multimodal capabilities to our state-of-the-art multilingual 8B and 32B models. 🌿 -
Poe
@poe_platform
Poe Apps Spotlight: LLMs continue to get smarter, but how well do they meme? MemeGenBattle is a fun new app on Poe that allows you to see for yourself. (1/2)
Poe
@poe_platform
MemeGenBattle is a good example of how Poe Apps can transform AI interaction beyond chat. Test Claude 3.7 Sonnet and GPT-4.5’s meme generating skills at poe.com/MemeGenBattle, or create your own app at poe.com/App-Creator. (2/2)
-
Poe
@poe_platform
Now on Poe: Wan 2.1!
Alibaba's new AI model creates impressive, high-quality videos from text and images. (1/2)
Poe
@poe_platform
Wan 2.1 is available to try at poe.com/Wan-2.1 and across all platforms. (2/2)
-
Poe
@poe_platform
Now available: Ray2 is on Poe!
@LumaLabsAI's next-gen video model transforms images into beautiful videos with remarkable realism. (1/2)
Poe
@poe_platform
We can’t wait to see how people use this with Poe Apps, which launched last week. Ray2 is available for you to try at poe.com/Ray2, and on all platforms. (2/2)
-
Poe
@poe_platform
Now on Poe: GPT-4.5!
OpenAI’s newest model excels in tasks that require creativity, emotional nuance, and extensive world knowledge. (1/2)
Poe
@poe_platform
GPT-4.5 is available at poe.com/GPT-4.5-Preview and on any of the Poe apps. (2/2)
-
Poe
@poe_platform
In building Poe Apps, we wanted to test interesting ways to combine multiple AI models into intuitive visual tools. Chibify is a fun example of what’s possible - transforming photos into 3D anime-style art by connecting GPT-4o with FLUX-Pro-1.1. (1/3)
Poe
@poe_platform
With Poe Apps, creators can focus on creativity rather than API management. Users can access powerful model combinations through new visual interfaces or build their own custom apps using App Creator. (2/3)
Poe
@poe_platform
You can try Chibify today at poe.com/Chibify, or create your own Poe App using our new App Creator: poe.com/App-Creator. (3/3)
-
Poe
@poe_platform
Introducing Poe Apps: a new, easy way to create and use visual interfaces into any combination of the 100+ text, image, video, and audio models on Poe. (1/5)
Poe
@poe_platform
We created Poe Apps to support AI use cases where chat is not as good as a visual interface. This might be true for workflows, games, quizzes, multimedia generation, document editing, or many other applications we hope you’ll create. (2/5)
Poe
@poe_platform
Poe App Creator, built on Claude 3.7 Sonnet, can automatically generate an app given a prompt. As an example, we created Chibify, which uses a combination of GPT-4o and FLUX-Pro-1.1 to transform photos into an anime-style picture. (3/5)
Poe
@poe_platform
All of this is uniquely possible on Poe because a wide variety of AI companies have made their models available here, and we pass along potentially-expensive inference costs to users, so that you as the creator of an application don’t have to worry about covering those costs. (4/5)
Poe
@poe_platform
You can try Poe Apps and our new App Creator today on web and desktop (iOS and Android coming soon).
To learn more, visit our blog at poe.com/blog/introducing-poe-apps. We're excited to see what you create! (5/5) -
Poe
@poe_platform
Claude 3.7 Sonnet is now available on Poe!
Anthropic’s most advanced model combines deep reasoning and performance with engaging conversation skills. (1/2)
Poe
@poe_platform
This will be especially helpful for solving complex problems and real-world coding tasks.
You can try it now on all Poe apps and at poe.com/Claude-3.7-Sonnet. (2/2) -
Poe
@poe_platform
Now on Poe: Veo 2!
Widely regarded as the world’s leading video generation model, Veo 2 generates stunning, realistic video from text prompts in a wide range of styles - and Poe is one of the only places you can use it! (1/2)
Poe
@poe_platform
You can try Veo 2 today at poe.com/Veo-2.0 and on all of the Poe apps. (2/2)
-
Poe
@poe_platform
We're launching chat history caching to help reduce point usage. If you send messages within five minutes of each other, the model can reuse parts of your chat history instead of starting from scratch. This reduces processing and saves you points. (1/5)
Post not available here, view on X
Poe
@poe_platform
For example, with OpenAI bots, a chat history of 24 cached messages could cost the same as 12 uncached ones.
With Anthropic bots, up to 120 cached messages could cost the same as 12 uncached ones. This means more context with fewer points used. (4/5)
Poe
@poe_platform
We hope this enables longer conversations and lower point usage. Enjoy! (5/5)
-
Poe
@poe_platform
New feature: /repeat. Get multiple responses from any bot by starting your message with /repeat, followed by a number and your prompt. (1/2)
Poe
@poe_platform
/repeat is particularly useful for image, video, or audio generation models, so you can choose the best response out of many variations.
You can try /repeat today at poe.com and across Poe apps on all platforms. (2/2) -
Poe reposted
Cohere Labs
@Cohere_Labs
Our state-of-the-art multilingual model, Aya Expanse, is now available on @poe_platform. 🔥
poe.com/Aya-Expanse-32B -
Poe
@poe_platform
You can now send new messages in a chat before a bot has finished responding. (1/2)
Poe
@poe_platform
This is useful for bots that take time to reply, especially reasoning models like R1 or o3-mini, or video generation models like Pika or Runway. As we get more powerful agents this year it will be especially important! (2/2)
-
Poe
@poe_platform
Now on Poe: Mistral Small 3! This latest model from Mistral AI is fast (150 tokens/second), knowledgeable (81% on MMLU benchmark), and excels at understanding and following instructions. (1/2)
Poe
@poe_platform
Mistral Small 3 is available at poe.com/Mistral-Small-3 and on all Poe apps. (2/2)
-
Poe
@poe_platform
New feature: Message multiple bots at the same time! 1/3
Poe
@poe_platform
This can be useful to compare results from the wide variety of models available on Poe, all in a single chat thread. 2/3
Poe
@poe_platform
To try it out, go to poe.com or open the Poe desktop app, @-mention the bots of your choice, add your message, and see how they all respond. 3/3
-
Poe
@poe_platform
o3-mini and DeepSeek R1 are now available as base models for prompt bots on Poe. (1/2)
Poe
@poe_platform
Get started at poe.com/create_bot. We’re excited to see the ideas people bring to building upon these powerful new reasoning models. (2/2)
-
Poe
@poe_platform
Google’s new Gemini 2.0 models are all available on Poe! Gemini 2.0 Pro, Flash, and Flash-Lite combine strong coding performance, speed, and the ability to handle the most complex prompts to date. (1/2)
Poe
@poe_platform
Try Gemini 2.0 Pro in beta at poe.com/Gemini-2.0-Pro, Gemini 2.0 Flash at poe.com/Gemini-2.0-Flash, and/or Gemini 2.0 Flash-Lite in beta at poe.com/Gemini-2.0-Flash-Lite; and across all Poe apps. (2/2)
-
Poe
@poe_platform
New on Poe: GPT-Researcher!
This open-source agent delivers detailed research reports in minutes, combining real-time information with accurate citations from trusted sources. (1/2)
Poe
@poe_platform
GPT-Researcher is designed to simplify research on any topic, from academic studies to technical deep dives and more. You can try it at poe.com/GPT-Researcher and across all of our Poe apps. (2/2)
-
Poe
@poe_platform
o3-mini, OpenAI’s newest reasoning model, is now available on Poe!
This is currently the most powerful model in the world for many use cases, and is especially strong for complex math, science, and coding tasks. (1/2)
Poe
@poe_platform
You can try o3-mini at poe.com/o3-mini, the enhanced o3-mini-high at poe.com/o3-mini-high, and on all Poe apps! (2/2)
-
Poe
@poe_platform
Now available on Poe: DeepSeek R1 distilled into Llama 70b running on @GroqInc!
This bot streams at hundreds of tokens per second using Groq custom hardware to reason as quickly as physically possible! (1/2)
Poe
@poe_platform
You can try DeepSeek-R1-Distill at poe.com/DeepSeek-R1-Distill and on all Poe apps. (2/2)
-
Poe
@poe_platform
We just launched a new reasoning category, featuring all of today’s reasoning models: DeepSeek R1, OpenAI o1 and o1-mini, Alibaba QwQ, and Fireworks f1 and f1-mini, all in one place. (1/2)
Poe
@poe_platform
You can try DeepSeek R1 at poe.com/DeepSeek-R1-FW (hosted by @FireworksAI_HQ, a US-based company), OpenAI’s o1 at poe.com/o1, and on all Poe apps. (2/2)
-
Poe
@poe_platform
Grok 2 is now available! This latest model from @xai features improved accuracy, better instruction following, image understanding, and multilingual support.
Additionally, the xAI team has created six different Grok 2-based prompt bots to show off its unique personality. (1/3)
Poe
@poe_platform
Each prompt bot showcases a unique aspect of Grok 2’s character and caters to diverse preferences. There's a bot that delivers witty roasts (RoastyGrok), another that deep-dives into fascinating topics (RabbitHoleGrok), and even one that brings chaotic fun (UnhingedGrok). (2/3)
Poe
@poe_platform
Grok 2 is available at poe.com/Grok-2. You can also try the unique prompt bots on the xAI page at poe.com/xai. All of these are available across each of the Poe apps. Enjoy! (3/3)
-
Poe
@poe_platform
Now #1 in the LMArena Text-to-Image leaderboard, @GoogleDeepMind's Imagen 3 has set new standards for image generation. You can try it today on Poe. (1/2)
Arena.ai
@arena
Breaking news from Text-to-Image Arena! 🖼️✨
@GoogleDeepMind’s Imagen 3 debuts at #1, surpassing Recraft-v3 with a remarkable +70-point lead! Congrats to the Google Imagen team for setting a new bar!
Try the best text2image at LMArena and cast your vote! More analysis👇
Poe
@poe_platform
Imagen 3 is available at poe.com/imagen3 and on all of the Poe apps! (2/2)
-
Poe
@poe_platform
Now on Poe: DeepSeek-R1!
This open-source reasoning model delivers comparable performance to o1, while pushing the boundaries with its advanced reasoning capabilities to solve complex problems in math, coding, and logical decision making. (1/2)
Poe
@poe_platform
DeepSeek-R1 is hosted by @togethercompute and available at poe.com/Deepseek-R1-T and on all Poe apps! (2/2)
-
Poe
@poe_platform
Now available: Pika 2.0!
This latest model from @pika_labs delivers improved video quality, better prompt adherence, and introduces Scene Ingredients, a new feature that lets you combine multiple images into video for greater control and consistency. (1/3)
Poe
@poe_platform
To use Scene Ingredients, simply upload images, add a prompt describing their interaction, and choose Precise (stays close to input) or Creative (gives Pika more freedom). For example, try adding a character, object, and location to see what it generates! (2/3)
Poe
@poe_platform
Pika 2.0 and Scene Ingredients are available at poe.com/Pika-2.0, and across all Poe apps! (3/3)
-
Poe
@poe_platform
DeepSeek-V3 is now available on Poe!
DeepSeek-V3 stands out as one of the most powerful open-source models available and excels in math, coding, and reasoning tasks. Its long context handling and performance across key benchmarks rival leading closed-source models. (1/2)
Poe
@poe_platform
It is hosted by @FireworksAI_HQ and available for you to try at poe.com/Deepseek-V3-FW and all Poe apps. (2/2)
-
Poe
@poe_platform
We’ve added @topazlabs' best-in-class image upscaler to Poe!
One-click upscale any image generated on Poe, or upload a photo directly to the bot for more control, including options to upscale by up to 16x. (1/3)
Poe
@poe_platform
To customize, you can use --upscale to set a factor between 2-16x, set your exact dimensions with --output_height and/or --output_width, and add --generated if your input is AI-generated. These options give you more control to create an upscaled image that fits your needs. (2/3)
Poe
@poe_platform
The Topaz Labs image upscaler is available at poe.com/TopazLabs, and as a follow up button after generating any image. It is available across all Poe apps. Enjoy! (3/3)
-
Poe
@poe_platform
OpenAI’s advanced reasoning model, o1, is now on Poe!
It’s faster and more powerful than o1-preview, and can reason over images using vision capabilities. (1/2)
Poe
@poe_platform
o1 is available at poe.com/o1 and on all Poe apps! (2/2)
-
Poe
@poe_platform
The updated Imagen 3 is now available!
Google DeepMind’s state-of-the-art image model can generate stunning visuals from detailed prompts across diverse styles, excelling in photorealism and accuracy. It outperforms leading models on key benchmarks, including quality. (1/2)
Poe
@poe_platform
You can try Imagen 3 at poe.com/Imagen3 and on all Poe apps! (2/2)
-
Poe
@poe_platform
Hailuo Live is now on Poe!
This new image-to-video model sets the standard for bringing images to life with high-quality motion. It generates smooth, consistent video across various styles with exceptional realism, consistency, and fluid movement. It is hosted by @fal. (1/2)
Poe
@poe_platform
It is available at poe.com/Hailuo-Live, and across all Poe apps! (2/2)
-
Poe
@poe_platform
Cartesia is now on Poe!
With @cartesia, you can choose between 100+ voices to convert text input or bot output to audio. This bot also supports 14 different languages, including Spanish, Japanese, and Chinese. (1/3)
Poe
@poe_platform
For example, you can pair Cartesia with Web Search bot to turn today’s top news into an entertaining and informative nostalgic radio broadcast using a specialty voice like 1920’s Radioman. (2/3)
Poe
@poe_platform
Generation times for the audio output vary based on the voice and length of copy. You can try Cartesia at poe.com/Cartesia, and across all Poe apps. Enjoy! (3/3)
-
Poe
@poe_platform
ElevenLabs is now on Poe!
Powered by their Turbo v2.5 model, this bot converts text into natural-sounding speech with various voice options. You can also try the new Speak button for easy audio output. Examples in the thread below: (1/6)Post not available here, view on X
Poe
@poe_platform
To change or try out the different voices, simply add ‘--voice [name]’ to the end of your message. There are 30 different voices so give them a try to find the best one for what you’re looking for. (5/6)
Poe
@poe_platform
You can try the Speak button as a follow up after any bot response, or copy and paste text you want to turn into an audio file at poe.com/ElevenLabs and across all Poe apps. Enjoy! (6/6)
-
Poe
@poe_platform
Llama 3.3 70B is now available on Poe!
It rivals the performance of the much larger Llama 3.1 405B, generates high-quality text responses, supports multiple languages, and has a 128k context window. (1/2)
AI at Meta
@AIatMeta
As we continue to explore new post-training techniques, today we're releasing Llama 3.3 — a new open source model that delivers leading performance and quality across text-based use cases such as synthetic data generation at a fraction of the inference cost.
Poe
@poe_platform
Llama 3.3 70B is hosted by @togethercompute. It is available at poe.com/Llama-3.3-70B and on all Poe apps. (2/2)
-
Poe
@poe_platform
QwQ-32B-Preview is now available on Poe!
This chain-of-thought based reasoning model from Alibaba is useful for advanced math, coding, and logical reasoning, achieving top-tier scores across various problem-solving benchmarks that rival those of other reasoning models. (1/2)
Poe
@poe_platform
This bot is hosted by @togethercompute. You can try it at poe.com/QwQ-32B-Preview-T and on all Poe apps. (2/2)
-
Poe
@poe_platform
New on Poe: Luma Photon!
Just released by @LumaLabsAI, Photon is an advanced text-to-image generator that outperforms leading models across several benchmarks for image quality, creativity, and adherence. (1/2)
Poe
@poe_platform
You can try Photon at poe.com/Luma-Photon, and the more efficient Photon Flash at poe.com/Luma-Photon-Flash. Both bots are available across all Poe apps! (2/2)
-
Poe
@poe_platform
Assistant can now generate images on Poe!
You can ask it to create an image, refine it, and even ask questions about the image. (1/2)
Poe
@poe_platform
Our upgraded Assistant bot is available at poe.com/Assistant and on all Poe apps! (2/2)
-
Poe
@poe_platform
Today we’re introducing new subscription options to expand access to Poe, including a low-cost plan and higher point options. These plans provide access to all premium bots from OpenAI, Anthropic, Google, xAI, Runway, Ideogram, and many other providers. (1/7)
Post not available here, view on X
Poe
@poe_platform
If you would like to explore these options today, visit poe.com and click “Subscribe” or "Upgrade" in the sidebar, select your preferred plan, and complete the payment. Note: These new subscription options are only purchasable through web and mobile web. (6/7)
Poe
@poe_platform
We're excited to provide everyone with more opportunities to explore AI capabilities. You can try Poe today at poe.com and across all Poe apps. (7/7)
-
Poe
@poe_platform
FLUX1.1 [pro] Ultra is now on Poe!
Generate stunning images up to 4x the resolution of FLUX1.1 [pro] with exceptional detail, adherence, and speed. You can also use Raw Mode (--raw) to create images with impressive realism, ideal for portraits and nature photography. [1/3]
Poe
@poe_platform
To use Raw Mode for images that look more natural, or to customize the aspect ratio, add '--raw' or '--aspect [desired ratio]' to your prompt.
For example: 'Portrait of a smiling young woman with multicolored hair, art studio background --raw --aspect 16:9'. (2/3)
Poe
@poe_platform
This best-in-class image generator is hosted by @FAL and is available at poe.com/FLUX-pro-1.1-ultra, and on all Poe apps. Enjoy! [3/3]
-
Poe
@poe_platform
The newly updated GPT-4o snapshot is available on Poe! It's been upgraded with improved creative writing capabilities and better insights for file uploads. (1/2)
Poe
@poe_platform
You can try the updated GPT-4o at poe.com/GPT-4o and on all Poe apps. (2/2)
-
Poe
@poe_platform
Llama 3.1 Nemotron is now available on Poe!
This model from Nvidia demonstrates strong performance in complex reasoning, problem-solving, and instruction following, as well as writing and coding tasks. (1/2)
Poe
@poe_platform
We’ve also made Llama 3.1 Nemotron available as a base for you to create prompt and server bots with!
This bot is hosted by @togethercompute. You can try it at poe.com/Llama-3.1-Nemotron and on all Poe apps. (2/2) -
Poe
@poe_platform
We’ve added the June 2024 version of Claude 3.5 Sonnet back to Poe! This is the version from before the recent update in October. It may be better for certain use cases. (1/2)
Poe
@poe_platform
Claude 3.5 Sonnet (June) is available at poe.com/Claude-3.5-Sonnet-June and across all Poe apps. Enjoy! (2/2)
-
Poe
@poe_platform
f1 and f1-mini, new state-of-the-art complex reasoning models from @FireworksAI_HQ, are now available on Poe! (1/2)
Lin Qiao
@lqiao
🔥 Introducing Fireworks f1 🔥
f1 is the first reasoning system over open models to beat GPT-4o and Claude 3.5 Sonnet across hard coding, chat and math benchmarks.
💥 two variants now available in preview: f1 and f1-mini
💥 access the preview on Fireworks AI Playground for free
💥 get on to waitlist for free early access to the f1 API
Read more: fireworks.ai/blog/f1-compound-ai-reasoning-model
Poe
@poe_platform
You can try the new f1-preview at poe.com/f1-preview, and f1-mini-preview at poe.com/f1-mini-preview. These bots are also available on all Poe apps. (2/2)
-
Poe
@poe_platform
Now on Poe: Qwen2.5-Coder-32B!
This versatile new model is top-tier in coding, matching or surpassing industry leaders in code-related benchmarks. It excels at code generation and debugging, supports over 40 programming languages, and can handle up to 128k tokens. (1/2)
Poe
@poe_platform
This bot is hosted by @hyperbolic_labs and is available at poe.com/Qwen2.5-Coder-32B and across all Poe apps! (2/2)
-
Poe
@poe_platform
You can now build custom prompt and server bots using Grok-beta as the base model on Poe!
Poe
@poe_platform
Grok-beta is now on Poe!
An early preview of xAI’s most intelligent model, Grok-beta offers cutting-edge reasoning capabilities and is well-suited for chat, coding, and complex multi-step tasks. (1/2) -
Poe
@poe_platform
Grok-beta is now on Poe!
An early preview of xAI’s most intelligent model, Grok-beta offers cutting-edge reasoning capabilities and is well-suited for chat, coding, and complex multi-step tasks. (1/2)
Poe
@poe_platform
This bot does not have access to real-time information from X or the internet as part of its integration with Poe.
It is available at poe.com/Grok-beta and across all of the Poe apps. (2/2) -
Poe
@poe_platform
Now available on Poe: Claude 3.5 Haiku!
The new Haiku model outperforms its predecessor across all metrics and exceeds Claude 3 Opus on several intelligence benchmarks. It’s fast, has improved instruction following, and is particularly strong with coding tasks. (1/2)
Poe
@poe_platform
Claude 3.5 Haiku is available at poe.com/Claude-3.5-Haiku and across all of the Poe apps! (2/2)
Poe
@poe_platform
We've also made Claude 3.5 Haiku available as a base bot for your custom prompt and server bots!
-
Poe
@poe_platform
Dream Machine from @LumaLabsAI is now available on Poe!
Generate videos, animate images, and build your own custom video bots using this state-of-the-art generative video model. (1/2)
Poe
@poe_platform
Dream Machine is available today at poe.com/Dream-Machine and available on all Poe apps. Looking forward to seeing what you create! (2/2)
-
Poe
@poe_platform
Recraft v3 (formerly Red Panda) is now available on Poe!
This breakthrough image model currently ranks #1 on the Image Arena, and is capable of generating incredibly detailed photorealistic pictures and the longest strings of text of any generator. (1/3)
Poe
@poe_platform
This bot also comes with 20 custom styles that you can append to your prompt, using the “--style” param. Here are examples using the prompt: “An old man holding a pizza over his head inside of a pizzeria” across four different styles. (2/3)
Poe
@poe_platform
Recraft v3 is hosted by @fal. You can try it at poe.com/Recraft-V3 and on all of the Poe apps. (3/3)
-
Poe
@poe_platform
Runway is now available on Poe!
Transform text or images into stunning cinematic video with the power of @RunwayML’s state-of-the-art Gen-3 Alpha Turbo model. (1/2)
Poe
@poe_platform
You can start generating videos with Gen-3 Alpha Turbo at poe.com/Runway and on all Poe apps. We’re excited to see what you create! (2/2)
-
Poe
@poe_platform
Stable Diffusion 3.5 Large is now on Poe!
Stability AI's most powerful model yet, this image generator delivers superior image quality, prompt adherence, and output diversity compared to its predecessor. (1/2)
Poe
@poe_platform
You can try Stable Diffusion 3.5 Large at poe.com/StableDiffusion3.5-L, or Stable Diffusion 3.5 Turbo for faster generations at poe.com/StableDiffusion3.5-T, as well as on all of the Poe apps. (2/2)
-
Poe
@poe_platform
Upgraded Claude 3.5 Sonnet is now on Poe!
This model sets new performance standards and leads the industry across key benchmarks. It is now the best available model for software tasks and coding, with significant improvements in speed, accuracy, and efficiency. (1/2)
Poe
@poe_platform
The upgraded Claude 3.5 Sonnet is available at poe.com/Claude-3.5-Sonnet, and across all Poe apps. (2/2)
-
Poe
@poe_platform
Hailuo AI is now available on Poe!
This best-in-class video bot is capable of generating stunning, high-quality video in a wide-variety of styles using text or image input. It is hosted by @fal. (1/2)
Poe
@poe_platform
Hailuo AI is available at poe.com/hailuo-ai and on all Poe apps. Enjoy! (2/2)
-
Poe
@poe_platform
Now available on Poe: @hyperbolic_labs’ Llama 3.1 405B Base, Hermes 3 70B, and more! (1/2)
Poe
@poe_platform
You can try Llama 3.1 405B Base and all of the Hyperbolic bots at poe.com/hyperbolic, and across all Poe apps! (2/2)
-
Poe
@poe_platform
Imagen 3 is now on Poe!
This fast, powerful image model from @GoogleDeepMind excels in photorealism, prompt adherence, and text within images. It can handle complex prompts, supports diverse formats and styles, and is particularly good at creating images of people. (1/2)
Poe
@poe_platform
Imagen 3 is available for you to try at poe.com/Imagen3 and across all Poe apps. For short, simple prompts and faster generation time, you can also try Imagen 3-Fast at poe.com/Imagen3-Fast. Looking forward to seeing what you create! (2/2)
-
Poe
@poe_platform
We’ve upgraded Assistant with web search capabilities!
Ask questions and get more accurate answers grounded in the latest real-time information. (1/2)
Poe
@poe_platform
Assistant is available at poe.com/Assistant and on all Poe apps. (2/2)
-
Poe
@poe_platform
FLUX1.1 is now available on Poe 🫐!
FLUX1.1 [pro] (also known as “blueberry”) is the most advanced image model currently available. It is 6x faster than it’s predecessor and features significant improvements in image quality and prompt adherence. (1/2)
Poe
@poe_platform
This bot is hosted by @fal and is available at poe.com/FLUX-pro-1.1, and across all Poe apps! (2/2)
-
Poe
@poe_platform
The just-released Llama 3.2 models are now available on Poe!
Llama 3.2 90B and 11B are cutting-edge multimodal models that show high-performance in vision-related tasks, including analyzing charts and graphs, describing images, and answering questions about pictures. (1/2)
Poe
@poe_platform
You can try Llama 3.2 90B at poe.com/Llama-3.2-90B-FW-131k, Llama 3.2 11B at poe.com/Llama-3.2-11B-FW-131k, and across all Poe apps! (2/2)
-
Poe
@poe_platform
Google’s new Gemini 1.5 Pro and Gemini 1.5 Flash are now on Poe! (1/4)
Post not available here, view on X
Poe
@poe_platform
Gemini 1.5 Flash delivers impressive speed improvements with 3x reduced latency and 2x faster output. This new version also offers improvements in reasoning, better handling of complex tasks, and high performance across text and visual inputs quickly. (3/4)
Poe
@poe_platform
You can try them across all Poe apps and at the following links:
poe.com/Gemini-1.5-Pro
poe.com/Gemini-1.5-Flash
poe.com/Gemini-1.5-Pro-128k
poe.com/Gemini-1.5-Flash-128k
poe.com/Gemini-1.5-Pro-2M
poe.com/Gemini-1.5-Flash-1M
Enjoy! (4/4) -
Poe
@poe_platform
We have removed the message limits for the o1-preview and o1-mini bots. Enjoy!
Poe
@poe_platform
OpenAI o1-preview and o1-mini are now available on Poe! (1/2)
OpenAI
@OpenAI
We're releasing a preview of OpenAI o1—a new series of AI models designed to spend more time thinking before they respond.
These models can reason through complex tasks and solve harder problems than previous models in science, coding, and math. openai.com/index/introducing-openai-o1-preview/ -
Poe
@poe_platform
We’ve upgraded Solar Mini to the new Solar Pro Preview! This new flagship model from @upstageai is smarter, more conversational, and better at instruction-following. (1/2)
Poe
@poe_platform
Solar Pro Preview is available to all users at poe.com/Solar-Pro-Preview and on all Poe apps. (2/2)
-
Poe
@poe_platform
OpenAI o1-preview and o1-mini are now available on Poe! (1/2)
OpenAI
@OpenAI
We're releasing a preview of OpenAI o1—a new series of AI models designed to spend more time thinking before they respond.
These models can reason through complex tasks and solve harder problems than previous models in science, coding, and math. openai.com/index/introducing-openai-o1-preview/
Poe
@poe_platform
You can try o1-preview at poe.com/o1-preview-128k and o1-mini at poe.com/o1-mini-128k. Both are available across all Poe apps effective immediately. Enjoy! (2/2)
-
Poe
@poe_platform
We've just made GPT-4-Classic-0314 available on Poe at poe.com/GPT-4-Classic-0314 and across all Poe apps.
🍓🍓🍓
@iruletheworldmo
@adamdangelo @poe_platform your classic gpt4 model points to 06 or something right?
i think many would sub (if they don't already) to get easy use in app to the gpt-4-0314 model
currently top of the sota benchmark ^^ @aidan_mclau -
Poe
@poe_platform
Thanks to everyone who attended our hackathon last weekend at @agihouse_org! We saw a variety of impressive submissions tackling a range of challenges. After a full day of building, we’re excited to highlight the winning projects:
Post not available here, view on X
Poe
@poe_platform
Kids School Lunch removes the guesswork out of packing school lunches each week. Answer five quick questions about your child’s tastes, and it generates a week's worth of lunch ideas, complete with kid-friendly recipes: poe.com/s/GWtzn14FIUzTVWR3R0Ze
Poe
@poe_platform
Thanks again to all the participants for their exceptional work last weekend. And a special thanks to our sponsors @FireworksAI_HQ and @modal_labs. If you’re interested in creating bots on Poe, our creator guide can show you how to get started: creator.poe.com/docs/welcome-to-poe-for-creators
-
Poe
@poe_platform
Playground v3 is now available on Poe! This state-of-the-art image model features cutting-edge prompt understanding, text-over-image capabilities, and can accept up to 8k token prompts. This allows you to have greater control, detail, and more accurate images. (1/2)
Poe
@poe_platform
We’ve also added Playground v3 as a base bot for your prompt bots! The expanded context window allows for more nuanced prompting, helping you define and generate your unique style consistently.
You can try it at poe.com/Playground-v3, and across all of the Poe apps. (2/2) -
Poe
@poe_platform
Ideogram 2.0 is now available on Poe! This model is the most advanced image generator available and excels at producing high-quality, lifelike images, especially for human features. It also offers industry-leading text rendering, seamlessly blending text into your images. (1/2)
Poe
@poe_platform
In addition, Ideogram 2.0 is also available as a base bot! You can try it out now at poe.com/Ideogram-v2, and on all Poe apps. (2/2)
-
Poe
@poe_platform
We’ve added support for longer video uploads, up to 350MB, to Gemini 1.5 Pro and Flash! Longer video uploads enable you to ask questions and get answers directly from the content, generate summaries, find specific moments, and much more. (1/2)
Poe
@poe_platform
You can try this today with Gemini 1.5 Pro poe.com/Gemini-1.5-Pro, Flash poe.com/Gemini-1.5-Flash, and across all Poe apps. (2/2)
-
Poe
@poe_platform
You can now generate Previews on Android!
Previews let you create and interact with web apps right inside your Poe chats using the latest state-of-the-art LLMs. It works particularly well with Claude 3.5 Sonnet, ChatGPT-4o-Latest, Gemini 1.5 Pro, and Llama 3.1 405B. -
Poe
@poe_platform
We've made it easier to share your Previews with a unique link! These shareable Previews are a frictionless way to showcase what you generate, allowing anyone with the link to interact directly within a dedicated canvas.
-
Poe
@poe_platform
We’ve made ChatGPT 4o Latest and Llama 3.1 405B available as base models for your custom bots on Poe! Creators can now use two of the most advanced LLMs around, as well as Llama 3.1 8B and 70B, to create customized prompt and server bots. Enjoy!
-
Poe reposted
Adam D'Angelo
@adamdangelo
We're hosting a hackathon this weekend for people to experiment with a more powerful version of the Poe Previews feature. There will be an in-person event at AGI House in the bay area, and a remote event as well.
Poe
@poe_platform
We’re excited to announce a one-day hackathon with @agihouse_org around our new Previews feature! Compete to create the most innovative and useful in-chat generative UI experiences using the latest LLMs like GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro, and Llama 3.1 405B. (1/3)
-
Poe
@poe_platform
ChatGPT-4o-latest is now on Poe! This model is #1 in the lmsys arena as of today, and you can try it using the link in the next message. (1/2)
OpenAI Developers
@OpenAIDevs
This model is also now available in the API as `chatgpt-4o-latest`. We recommend `gpt-4o-2024-08-06` for most API usage, but are excited to give developers access to test our latest improvements for chat use cases.
platform.openai.com/docs/models/gpt-4o
Poe
@poe_platform
ChatGPT-4o-latest is available at poe.com/ChatGPT-4o-Latest, a longer context version at poe.com/ChatGPT-4o-Latest-128k, and across all Poe apps. Enjoy! (2/2)
-
Poe
@poe_platform
Previews are now available on the Poe iOS app! Generate custom interactive apps directly in chat using any of the leading LLMs, including Claude 3.5 Sonnet, GPT-4o, Gemini 1.5 Pro, and Llama 3.1 405b. (1/4)
Post not available here, view on X
Poe
@poe_platform
All Previews created on Poe can be shared via a custom link, allowing others to try or remix your apps. And with cross-device syncing, you can build and edit your Previews on the Poe app or via the website. (3/4)
Poe
@poe_platform
To celebrate the expanded release, we’re partnering with @agihouse_org for a Previews hackathon where you’ll compete to create the most innovative and useful in-chat generative UI experiences. All creators are welcome. You can learn more here: app.agihouse.org/events/poe-previews-hackathon-20240817 (4/4)
-
Poe
@poe_platform
You can now build custom image bots on Poe using any FLUX model! FLUX pushes the limits of what's possible with image generation, allowing you to create custom prompt and server bots that generate high-quality pictures in any style you want - and monetize them.
-
Poe reposted
Shaun Ralston
@shaunralston
Wow. FLUX.1 Pro on @poe_platform; best kept secret w/access to best LLMs, image generators, custom bots, coding w/artifact windows; super friendly w/o need for complex integrations or multiple subs. Great work @adamdangelo ~ Poe is lit 🔥
-
Poe
@poe_platform
We’re excited to announce a one-day hackathon with @agihouse_org around our new Previews feature! Compete to create the most innovative and useful in-chat generative UI experiences using the latest LLMs like GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro, and Llama 3.1 405B. (1/3)
Poe
@poe_platform
Previews lets you build interactive web apps directly in chat with AI. For this event, we’re looking for standout apps that showcase real-world utility. We encourage leveraging external APIs and multiple AI models to push the boundaries of what's possible in chat. (2/3)
Poe
@poe_platform
This hackathon will feature a live keynote from @adamdangelo and hands-on support from the Poe team. AI developers and creators of all skill levels are encouraged to participate. You can apply for in-person or remote participation here: app.agihouse.org/events/poe-previews-hackathon-20240817 (3/3)
-
Poe
@poe_platform
The just-released Flux.1 text-to-image models are now available on Poe!
Flux.1[pro] sets new standards in image quality, prompt adherence, and typography, generating stunning images with impressive detail quickly. (1/2)
Poe
@poe_platform
The Flux.1 bots are hosted by @FAL. You can try Flux.1[pro] at poe.com/flux-pro, the efficient Flux.1[dev] at poe.com/flux-dev, the turbo-speed Flux.1[schnell] at poe.com/flux-schnell, and across all Poe apps. (2/2)
-
Poe
@poe_platform
Now on Poe: Mistral Large 2! The newest flagship model from Mistral, Large 2 demonstrates frontier-level performance and significant improvements in code generation, math, and reasoning. (1/2)
Poe
@poe_platform
This model is better than its predecessor in several other areas including instruction following, multi-turn conversations, accuracy, and multilinguality. You can try it today at poe.com/Mistral-Large-2, and across all Poe apps. (2/2)
-
Poe
@poe_platform
You can now create videos on Poe with @pika_labs and LivePortrait hosted by @FAL!
With Pika, you can generate unique video from text, image, and video input in seconds. (1/4)
Poe
@poe_platform
We’ve also added a new animate button that lets you bring any generated image to life with one click, and made Pika available as a base bot for creators to build custom prompt and server bots! (2/4)
Poe
@poe_platform
You can also bring images to life with LivePortrait. This bot animates images using video input, transforming your uploaded picture and short expressive video into a new animated clip. (3/4)
Poe
@poe_platform
These video bots are available at poe.com/Pika, poe.com/LivePortrait, and across all Poe apps. We look forward to seeing what you create! (4/4)
-
Poe
@poe_platform
Llama 3.1 405B is now on Poe! This new model is the first frontier-level open source AI model, outperforming leading models across multiple benchmarks. It excels in long-context understanding, mathematical reasoning, multilingual tasks, and general knowledge. (1/2)
Poe
@poe_platform
You can try the new Llama 3.1 405B by @togethercompute at poe.com/Llama-3.1-405B-T, and the longer context version hosted by Fireworks AI at poe.com/Llama-3.1-405B-FW, and on all Poe apps. (2/2)
-
Poe
@poe_platform
GPT-4o mini is available on Poe!
GPT-4o mini is OpenAI’s newest model and the highest performing small model available. Benchmark evaluations show it surpasses other compact models in reasoning (text and vision), math, and coding tasks. (1/2)
Poe
@poe_platform
You can try GPT-4o mini at poe.com/GPT-4o-Mini, the longer context version at poe.com/GPT-4o-Mini-128k, and across all apps. (2/2)
-
Poe
@poe_platform
You can now upscale your images on Poe with the @playground_ai upscaler! This bot will sharpen and add ultra-fine detail to any uploaded or generated image, increasing the resolution by 4x. It can also improve the definition and clarity of low-res photos. (1/2)
Poe
@poe_platform
You can give the Playground upscaler a try directly at poe.com/PlaygroundUpscaler, or as a dynamic follow up with any image generator across all Poe apps. (2/2)
-
Poe
@poe_platform
“Create a functional game of Snake, but make it cuter…”
-
Poe
@poe_platform
We’re excited to introduce Previews, a new feature that lets you see and interact with web applications generated directly in chats on Poe. Previews works particularly well with LLMs that excel at coding, including Claude 3.5 Sonnet, GPT-4o, and Gemini 1.5 Pro. (1/5)
Post not available here, view on X
Poe
@poe_platform
Previews is available now for all users on web, and supports HTML output, with CSS and Javascript functionality. We plan to introduce support for additional formats in the coming days and weeks. We’re excited to see what you create! (4/5)
Poe
@poe_platform
The Previews highlighted above are available for you to try here:
Interactive Presentation: poe.com/s/NlX2WRElDUvtuuMSFrZq
Flashcards: poe.com/s/HDAXQjBX9qmsInjjgV4X
Drum Machine: poe.com/s/G4HshkCQCaXVfg0ndPZK
Large Color Collider: poe.com/s/neKbyqEJYUtiRjeC6b5f (5/5) -
Poe
@poe_platform
We’ve just released an updated version of Gemini 1.5 Flash with Google search capabilities. This new bot incorporates real-time information to provide more accurate, reliable, and dynamic responses to your queries. (1/2)
Poe
@poe_platform
Gemini 1.5 Flash Search is available at poe.com/Gemini-1.5-Flash-Search and across all Poe apps. (2/2)
-
Poe
@poe_platform
Gemini 1.5 Pro on Poe now supports an industry-leading 2M token context length! With the expanded capacity, this bot can process multimodal information equivalent to 1.4M words or 14-20 books with near-perfect recall. (1/2)
Poe
@poe_platform
You can try Gemini 1.5 Pro 2M at poe.com/Gemini-1.5-Pro-2M and on all Poe apps. (2/2)
-
Poe
@poe_platform
Claude 3.5 Sonnet is available on Poe!
Claude 3.5 Sonnet is Anthropic’s best model yet and pushes the boundaries of what’s possible with AI. It sets new benchmarks in reasoning, knowledge, and coding, and features improvements in image understanding, writing, and more. (1/2)
Poe
@poe_platform
We’ve also made it available as a base for your prompt and server bots. You can try Claude 3.5 Sonnet at poe.com/Claude-3.5-Sonnet and the longer context version at poe.com/Claude-3.5-Sonnet-200k, and on all Poe apps. (2/2)
-
Poe
@poe_platform
We’re excited to share two major updates for creators on Poe: an upgraded creator analytics dashboard and the global expansion of price per message! Creators in 23 countries and regions can now set a price per message for their bots and earn revenue with each user message. (1/5)
Post not available here, view on X
Poe
@poe_platform
These enhanced analytics will help you understand how your bots are used over time, identify patterns in user interaction, and measure the impact of message pricing on bot usage and revenue. (4/5)
Poe
@poe_platform
We're excited to provide creators with more tools to help generate revenue and understand bot performance. Monetized creators can visit the upgraded creator dashboard and get started with setting a price per message for their bots at poe.com/creators. (5/5)
-
Poe
@poe_platform
Stable Diffusion 3 Medium is now on Poe! SD3 Medium is the latest image model from Stability AI and is capable of generating impressive images exceptionally fast. It is particularly good at understanding detailed prompts, text generation, and photorealism. (1/2)
Poe
@poe_platform
SD3 Medium is hosted by @FAL and available at poe.com/StableDiffusion3-2B and across all Poe apps!
-
Poe
@poe_platform
Qwen2-72B is now on Poe! This new model demonstrates top-tier performance in academic and chat benchmarks, and excels in coding, mathematics, reasoning, and multilingual capabilities. It is currently #1 on the HuggingFace Open LLM Leaderboard. (1/2)
Poe
@poe_platform
This bot is hosted by @FireworksAI_HQ and is available at poe.com/Qwen2-72b-Chat and on all Poe apps! (2/2)
-
Poe
@poe_platform
You can now build custom image bots on Poe using @ideogram_ai! This state-of-the-art model excels at text rendering and prompt adherence, allowing you to create bots that generate high-quality images in any style you define.
-
Poe
@poe_platform
New: @ideogram_ai is on Poe! This cutting-edge image generation model excels at creating high-quality images from text prompts. Its exceptional prompt adherence and state-of-the-art text rendering allow it to handle a wide range of creative requests. (1/2)
Poe
@poe_platform
Ideogram is available at poe.com/Ideogram and across all Poe apps! (2/2)
-
Poe reposted
Andrew Altshuler
@1eo
Amazing feature of @poe_platform
→ Run the prompt through several LLMs
→ Get multiple outputs
→ Filter/combine the best parts
→ Run again to integrate & make the output coherent✨ -
Poe
@poe_platform
Multi-bot chat allows you to seamlessly combine the unique strengths of different bots to complete tasks. For example, using @fal_ai_data’s latest bots, you can generate an image and remove the background within one conversational thread for a more efficient workflow. (1/2)
Poe
@poe_platform
You can try Fal AI’s Pixel Artist bot at poe.com/pixel-artist-bot and their background remover at poe.com/remove-background, and on all Poe apps. (2/2)
-
Poe reposted
Wil Reynolds
@wilreynolds
Here is how I'm trying to stay on top of 10 or more different major LLMs all in one chrome tab.
Pick a few queries you know a lot about
Put them in @poe_platform
Run them one after the next
Pick a model to summarize the output of all the other models to catch hallucinations
Re-run weekly / monthlyThis media couldn't be displayed. See it on the original post. -
Poe
@poe_platform
You can now build prompt and server bots using Gemini 1.5 Pro and Gemini 1.5 Flash on Poe! These state-of-the-art multimodal models from Google can handle context windows up to 1 million tokens, enabling you to create highly specialized bots with long context understanding.
-
Poe
@poe_platform
We’ve added GPT-4o and the longer context GPT-4o-128k as base bots on Poe! Creators can now build and monetize prompt and server bots on top of OpenAI’s newest and most advanced model. Looking forward to seeing what you create!
-
Poe
@poe_platform
Gemini 1.5 Flash and the upgraded Gemini 1.5 Pro are now on Poe! (1/5)
Post not available here, view on X
Poe
@poe_platform
You can try the upgraded Gemini 1.5 Pro at poe.com/Gemini-1.5-Pro, poe.com/Gemini-1.5-Pro-128k, poe.com/Gemini-1.5-Pro-1M, and on all Poe apps. (3/5)
Poe
@poe_platform
Gemini 1.5 Flash is a fast and lightweight, yet powerful multimodal model with impressive long-context understanding. It has up to a one-million-token context window, which is the equivalent of 30,000 lines of code or 700,000 words. (4/5)
Poe
@poe_platform
Gemini 1.5 Flash is available at poe.com/Gemini-1.5-Flash, a 128k context version at poe.com/Gemini-1.5-Flash-128k, a 1M context version at poe.com/Gemini-1.5-Flash-1M, and across all Poe apps. (5/5)
-
Poe
@poe_platform
Now available on Poe: Snowflake Arctic! This top-tier open-source model is designed for enterprise tasks, including generating SQL, writing code, and instruction following. It is hosted by @togethercompute. (1/2)
Poe
@poe_platform
You can try Snowflake Arctic today at poe.com/Snowflake-Arctic-T and across the Poe apps. (2/2)
-
Poe
@poe_platform
GPT-4o is now available on Poe across all platforms! This new frontier model from OpenAI is faster and more advanced than GPT-4 Turbo, and features improvements in vision capabilities, multilingual support, and coding. (Link in next tweet)
Poe
@poe_platform
GPT-4o is available at poe.com/GPT-4o and on all Poe apps. We’re excited for you to try it!
-
Poe
@poe_platform
New on Poe: Qwen1.5-110B! This multilingual model from Alibaba features comparable performance to other state-of-the-art open-source models on key benchmarks, with a particular strength in Chinese-language queries. (1/2)
Poe
@poe_platform
Qwen1.5-110B-T is hosted by @togethercompute, and is available at poe.com/Qwen-1.5-110B-T and on all Poe apps. (2/2)
-
Poe reposted
The Singularity Project
@01Singularity01
Poe is one of the few AI related products out there that brings real value. It's really worth it to pay for the Pro version. I never recommend anything, but I do recommend Poe.
Poe
@poe_platform
You can now build custom image bots using Stable Diffusion 3 and SD3-Turbo on Poe! These advanced models excel at complex prompts, typography, and image quality, allowing you to design specialized bots with consistent image outputs based on your custom prompts.
-
Poe
@poe_platform
You can now build custom image bots using Stable Diffusion 3 and SD3-Turbo on Poe! These advanced models excel at complex prompts, typography, and image quality, allowing you to design specialized bots with consistent image outputs based on your custom prompts.
-
Poe
@poe_platform
Gemini 1.5 Pro with Search is now available on Poe! This bot can access real-time information via Google Search to provide more accurate and relevant responses with citations. (1/4)
Post not available here, view on X
Poe
@poe_platform
We’ve also integrated Google Search capabilities into the recently-updated Gemini Pro, allowing it to deliver more reliable and informative responses. (3/4)
Poe
@poe_platform
You can try Gemini 1.5 Pro with Search at poe.com/Gemini-1.5-Pro-Search, and the updated Gemini Pro at poe.com/Gemini-Pro-Search, and across all Poe apps! (4/4)
-
Poe
@poe_platform
Groq-powered inference for Llama 3 is now available on Poe! You can use Llama-3-70b-Groq and experience the state-of-the-art open source model with near-instant streaming. (1/2)
Poe
@poe_platform
Both poe.com/Llama-3-70b-Groq and poe.com/Llama-3-8b-Groq are available across the Poe iOS, Android, Mac, and Windows apps. (2/2)
-
Poe
@poe_platform
Now on Poe: Command R and Command R+ from Cohere! These bots excel at understanding complex questions and long conversations, providing detailed answers in over 10 languages. They can also search the web for the latest information to enhance their responses. (1/2)
Poe
@poe_platform
Command R is accessible at poe.com/Command-R and Command R+ is at poe.com/Command-R-Plus. Both bots are also available across all Poe apps. (2/2)
-
Poe
@poe_platform
New: Stable Diffusion 3 is on Poe! SD3 is the latest image generation model from Stability, and it is especially good at typography and prompt accuracy. It understands complex prompts, supports multiple languages, and has improved spelling over SDXL. (1/2)
Poe
@poe_platform
Stable Diffusion 3 and the faster SD3 Turbo are hosted by @FireworksAI_HQ and available at SD3 poe.com/StableDiffusion3, and SD3-Turbo poe.com/SD3-Turbo, and across all Poe apps. We look forward to seeing what you create! (2/2)
-
Poe
@poe_platform
Llama 3 is now available on Poe! Llama 3 70B is now the most powerful open source model available, with state-of-the-art performance across industry benchmarks. It delivers new capabilities like enhanced reasoning, better code generation, and improved instruction following. (1/2)
Poe
@poe_platform
Both Llama 3 8B and 70B are available at poe.com/Llama-3-8B-T and poe.com/Llama-3-70B-T and across all Poe apps. (2/2)
-
Poe
@poe_platform
New: GPT-4 128k is now available as a base for prompt bots! The longer context window coupled with the power of the latest GPT-4 update should enable a variety of new use cases. Enjoy!
-
Poe reposted
VentureBeat
@VentureBeat
Poe introduces multi-bot chat and plans enterprise tier to dominate AI chatbot market venturebeat.com/ai/poe-introduces-multi-bot-chat-and-plan…
-
Poe
@poe_platform
Reka Core is now available on Poe! This state-of-the-art multimodal model matches leading LLMs in key evaluation metrics around reasoning, advanced coding, and multilingual capabilities, and is state of the art at understanding short videos. (1/2)
Reka
@RekaAILabs
Meet Reka Core, our best and most capable multimodal language model yet. 🔮
It’s been a busy few months training this model and we are glad to finally ship it! 💪
Core has a lot of capabilities, and one of them is understanding video --- let’s see what Core thinks of the 3 body trailer.👇
Poe
@poe_platform
Reka Core is available at poe.com/RekaCore and across all Poe apps. (2/2)
-
Poe
@poe_platform
Multi-bot chat is now available on Poe! Compare responses from multiple bots and add any bot with an @-mention - all within a single conversational thread. (1/4)
Adam D'Angelo
@adamdangelo
Today we are adding an important new capability to Poe: multi-bot chat. This feature lets you easily chat with multiple models in a single thread. (1/n)
Post not available here, view on X
Poe
@poe_platform
And to better represent this shift to a multi-bot experience, our brand is evolving with a new logo representing what’s now possible on Poe - and what’s coming in the future. (3/4)
Poe
@poe_platform
You can try multi-bot chat out today on web at poe.com and on Android. Full support for iOS is coming soon. Enjoy! (4/4)
-
Poe
@poe_platform
Now on Poe: Mixtral 8x22B! This bot, hosted and fine-tuned by @FireworksAI_HQ, is among the first instruct-tuned variants of the new Mixtral 8x22B model. (1/2)
Poe
@poe_platform
You can try it at poe.com/Mixtral8x22b-Inst-FW and across all Poe apps. Enjoy! (2/2)
-
Poe
@poe_platform
We’ve updated GPT-4 and GPT-4 128k in Poe to the new, greatly improved version of GPT-4 Turbo!
-
Poe
@poe_platform
Now on Poe: Gemini 1.5 Pro! This powerful new multimodal model from Google introduces an industry-leading context window of 1 million tokens (~700,00 words) with near-perfect retrieval, enabling complex tasks that require long-context understanding. (1/4)
Post not available here, view on X
Poe
@poe_platform
We’ve also added an upgraded version of the original Gemini Pro. This bot has been fine-tuned with a more conversational personality, and features quality improvements in areas such as reasoning, math, latency, storytelling, and summarization. (3/4)
Poe
@poe_platform
You can try the updated Gemini Pro at poe.com/Gemini-Pro and on all Poe apps. (4/4)
-
Poe
@poe_platform
Price per message is now available for creators on Poe! (1/2)
Adam D'Angelo
@adamdangelo
Today we’re introducing a new way for model developers and bot creators to generate revenue on @poe_platform: price per message! Creators can now set a per-message price for their bots and generate revenue every time a user messages them. Thread 👇
Poe
@poe_platform
To get started, visit your bot edit page today and set your price. While this is currently limited to creators in the U.S.A, we plan to expand price per message to additional countries and regions soon! (2/2)
-
Poe reposted
Cerebral Valley
@cerebral_valley
Kicking off the @poe_platform hackathon with @adamdangelo!!
-
Poe reposted
Adam D'Angelo
@adamdangelo
Looking forward to the Poe hackathon tomorrow! If you're in the bay area, join us for early access to our new developer revenue sharing program and a view into the future of Poe and the surrounding ecosystem. Link in next tweet.
-
Poe
@poe_platform
We've added Claude 3 Opus 200k and Sonnet 200k as bases for your prompt bots! These multimodal models are the most powerful base bots available, and can handle longer inputs for more natural back-and-forth conversations, in-depth analysis, multi-step tasks, and more.
-
Poe
@poe_platform
New on Poe: DBRX Instruct! This leading-edge open source model excels at a wide range of tasks, including language understanding, programming, logic, and math, and has been fine-tuned to specialize in few-turn interactions. (1/2)
Poe
@poe_platform
DBRX Instruct is hosted by @FireworksAI_HQ. You can try it today at poe.com/dbrx-instruct-fw and across all Poe apps. (2/2)
-
Poe
@poe_platform
We’re excited to announce a Poe hackathon on April 6th around our upcoming creator monetization system: price per message! Attendees will get first access to the ability to set a per-message price for their bots and generate revenue every time a user messages them. (1/4)
Post not available here, view on X
Poe
@poe_platform
Being able to reliably generate revenue with every message allows developers creating bots with significant GPU inference costs or API costs to build sustainable, profitable businesses, and we are excited to see the ecosystem this enables. (3/4)
Poe
@poe_platform
This hackathon is in partnership with @cerebral_valley and @SHACK15sf, and will feature a keynote from @adamdangelo and includes hands-on support from the Poe team.
If you’re in the Bay Area, come build a bot and monetize it: partiful.com/e/5e04bH25WI0Vkx7XwZMj (4/4) -
Poe
@poe_platform
Now available on Poe: GPT-4 Classic! For anyone who preferred the original GPT-4 over Turbo, this bot lets you access the June 2023 GPT-4 model. (1/2)
Poe
@poe_platform
You can try it today at poe.com/GPT-4-Classic and across all Poe apps. Enjoy! (2/2)
-
Poe
@poe_platform
Claude 3 Opus, Sonnet, and Haiku are now available as a base for you to build prompt bots with on Poe! These powerful multimodal models are the best in the world for many use cases and support text and image input.
We’re excited to see what you create with them! -
Poe
@poe_platform
Claude 3 Haiku is now available on Poe! Haiku is Anthropic’s newest, fastest and most compact model in the Claude 3 family, and is capable of delivering near-instant replies. (1/2)
Poe
@poe_platform
Claude 3 Haiku is available in short context at poe.com/Claude-3-Haiku and 200k context at poe.com/Claude-3-Haiku-200k. These bots are available now across all Poe apps! (2/2)
-
Poe
@poe_platform
DeepSeek-Coder 33B is now on Poe, thanks to @togethercompute! This bot has advanced coding capabilities for multiple programming languages and can support users in a variety of coding-related tasks. (1/3)
Poe
@poe_platform
In addition to DeepSeek-Coder, Together AI released three additional bots on Poe: Gemma Instruct 7B, Qwen Chat 72B, and CodeLlama 70B. All four of these new bots are available for Poe users today. (2/3)
Poe
@poe_platform
You can try them at poe.com/DeepSeek-Coder-33B-T, poe.com/Gemma-Instruct-7B-T, poe.com/Qwen-72B-T, and poe.com/CodeLlama-70B-T. Enjoy! (3/3)
-
Poe
@poe_platform
We’ve released two new image generation features on Android! First is resend, which lets you generate a new image with the same prompt as the previous message in one click. Second is the ability to attach and remix images with bots based on StableDiffusionXL and Playground. (1/2)
Poe
@poe_platform
Resend and Remix are available on the latest version of the Poe app for Android! (2/2)
-
Poe
@poe_platform
We’ve updated all Claude 3 bots to support image uploads! You can add images directly into your conversations using the attachment button.
This feature is live on Poe on all platforms. -
Poe
@poe_platform
New on Poe: MythoMax-L2-13B as a base bot for prompt bots! This popular text-generation model is well-suited for creative interactions including storytelling, roleplaying, and creative writing. (1/2)
Poe
@poe_platform
You can try MythoMax-L2-13B at poe.com/MythoMax-L2-13B and across all Poe apps. Enjoy! (2/2)
-
Poe
@poe_platform
Now available: Claude-3-Opus-200k and Claude-3-Sonnet-200k! The expanded context windows on Opus and Sonnet allow you to now input vast amounts of information with near-perfect recall, making them great for complex tasks and multi-step instructions. (1/2)
Poe
@poe_platform
You can try them at poe.com/Claude-3-Opus-200k and poe.com/Claude-3-Sonnet-200k (2/2)
-
Poe
@poe_platform
Claude 3 is now available on Poe across all platforms! Claude 3 Opus was released this morning by Anthropic and is the highest quality model on the market, showing the outer limits of what is possible with AI today. Links in next tweet.
Poe
@poe_platform
You can use Opus at poe.com/Claude-3-Opus and Sonnet at poe.com/Claude-3-Sonnet.
-
Poe
@poe_platform
Groq-powered inference for Mixtral is now available on Poe! You can use Mixtral-8x7b-Groq and experience 400 token/second responses. (1/2)
Poe
@poe_platform
The bot is available at poe.com/Mixtral-8x7b-Groq and across the Poe iOS, Android, Mac, and Windows apps in the official bots category. (2/2)
-
Poe
@poe_platform
Now available: Gemini Pro 1.0 as a base bot! This multimodal bot accepts text, image, and video input, and has been upgraded with overall quality improvements, including improved reasoning, better latency, and multilingual support. We look forward to seeing what you build!
-
Poe
@poe_platform
Just launched: Playground v2.5 on Poe! This new image model produces more realistic and visually compelling images, with key improvements in color vibrancy and contrast, finer human-related details, and multi-aspect ratio support. (1/3)
Poe
@poe_platform
Playground’s internal evaluation and user studies have found that v2.5 demonstrates a significant increase in aesthetic quality and outperforms almost all other models. (2/3)
Poe
@poe_platform
Playground v2.5 is available now at poe.com/Playground-v2.5 and across all Poe apps. (3/3)
-
Poe
@poe_platform
Mistral Large, released by Mistral this morning, is now available to all users on Poe! This is the strongest Mistral model available so far and Poe is the easiest place to use it across all platforms: web, iOS, Android, MacOS, and Windows. (1/2)
Poe
@poe_platform
We are still in the process of evaluating it, but it appears to approach GPT-4, Claude 2, and Gemini in terms of quality, while including its own strengths, weaknesses, and biases. You can try it at: poe.com/Mistral-Large. Enjoy!
-
Poe
@poe_platform
Now on Poe: Gemma 7b-FW! Google's new lightweight model is built from the same research and technology as the Gemini models, and outperforms similar sized open models in general language understanding, reasoning, math, and coding, according to their internal evaluations. (1/2)
Poe
@poe_platform
Gemma-7b-FW is hosted by @FireworksAI_HQ. It’s available now at poe.com/Gemma-7b-FW and across all Poe apps. (2/2)
-
Poe
@poe_platform
Reka Flash from @RekaAILabs is now available on Poe! Reka Flash is a state-of-the-art 21B multimodal language model that works with text, image, and short video input. Reka Flash is highly capable and very performant for its size. (1/2)
Poe
@poe_platform
You can try Reka Flash today at poe.com/RekaFlash or via the Poe apps available on all platforms.
-
Poe
@poe_platform
New today: image understanding! We’ve enabled GPT-4v in all GPT-4 conversations, AND added LLaVa-based image understanding for almost all other bots on Poe. You can add images directly to your conversations using the attachment button next to the input box. (1/3)
Poe
@poe_platform
Image understanding works well for a variety of tasks. For instance, you can upload a photo and ask Assistant to describe it, attach a graph and have GPT-4 explain the data, or even add a picture of a dish and ask Mistral Medium to share the recipe for it. (2/3)
Poe
@poe_platform
We're excited to see how you use image understanding. It's available immediately on web and across all Poe apps on all platforms! (3/3)
-
Poe
@poe_platform
Code-Llama-70B-FW is now available on Poe! Hosted by @FireworksAI_HQ, CodeLlama-70B is the largest and best-performing model in the Code Llama family, and one of the highest performing open source code models available. (1/2)
Poe
@poe_platform
Code-Llama-70B-FW is available at poe.com/Code-Llama-70B-FW and across all Poe apps. Enjoy! (2/2)
-
Poe
@poe_platform
Image Remix is now available on iOS! Create custom versions of any generated or uploaded image simply by modifying the prompt. Give it a try on any bot based on SDXL or Playground-v2 and share what you create!
-
Poe
@poe_platform
We’ve added Mixtral 8x7B as a base model for bot creation! All Poe users can now create prompt bots on Mixtral-8x7B-Chat, a chat fine-tuned version of one of the strongest open source models. We can’t wait to see what you build!
-
Poe
@poe_platform
New on Poe: Image remix! Customize the style, layout, colors and other aspects of a generated or attached image by editing the prompt given to any bot based on SDXL or Playground v2! (1/3)
Poe
@poe_platform
For example: let’s say you generate an image of two cute kittens, but now you want to change the background. By clicking ‘Remix’ and altering the prompt, you’re able to make the desired changes to your image while maintaining the consistency from the original generation. (2/3)
Poe
@poe_platform
Image remix is currently available in all image generation bots based on SDXL and Playground v2 on Web, macOS, and Windows, with support for iOS and Android coming soon. Enjoy! (3/3)
-
Poe
@poe_platform
We’ve upgraded Solar-0-70b to the new Solar Mini! A smaller, yet faster and more powerful model than its predecessor, Solar Mini is now available to all Poe users. (1/2)
Poe
@poe_platform
Solar Mini is hosted by Upstage and available at poe.com/Solar-Mini and across all Poe apps! (2/2)
-
Poe
@poe_platform
We’re increasing payouts for creators! Bot creators can now earn up to $50 for each new subscriber their bots attract on Poe.
-
Poe
@poe_platform
You can now build image generating bots using Playground v2 as your base model!
Playground v2 is a powerful image model that delivers cutting-edge visuals with a focus on aesthetic quality and impressive accuracy. We’re excited to see the bots you build on it! -
Poe reposted
Adam D'Angelo
@adamdangelo
We are excited to announce that Quora has raised $75M from Andreessen Horowitz. This funding will be used to accelerate the growth of Poe, and we expect the majority of it to be used to pay bot creators through our recently-launched creator monetization program. (thread)
-
Poe reposted
Paul Jun
@PaulJun_
shoutout @poe_platform for finally making something people want: an easy way to create a bot using my past writing without any wild formatting or coding. Just drop PDFs or docs into it.
Very impressive how well it gives me the insights I want + sources. -
Poe
@poe_platform
Custom knowledge bases can help enhance your bot by offering external knowledge beyond what an LLM holds, helping you deliver an exceptional and unique experience for users.
They’re also easy to add on Poe. Here’s a quick tutorial on how to add a knowledge base to your bot: -
Poe
@poe_platform
Mistral-Medium is now available on Poe!
This is Mistral AI’s largest and most powerful model, performing better than Mixtral-8x7b and Mistral-7b on benchmarks across the board. (1/2)
Poe
@poe_platform
Try Mistral-Medium at poe.com/Mistral-Medium or via the Poe apps on all platforms! (2/2)
-
Poe
@poe_platform
Our creator monetization program is expanding to 17 new countries today!
More bot creators across the globe will now have the opportunity to earn revenue from their bots on Poe. (1/3)
Poe
@poe_platform
In addition to the USA, the 17 new countries include: Argentina, Australia, Belgium, Canada, Colombia, Germany, Hong Kong, India, Ireland, Italy, Japan, Mexico, Portugal, Singapore, Spain, Switzerland, and the United Kingdom. (2/3)
Poe
@poe_platform
You can build your bot on top of LLMs like GPT-4, Claude 2, DALL-E 3, and SDXL, customize it with a knowledge base, and reach a worldwide audience of millions. Visit poe.com/creators to join! (3/3)
-
Poe
@poe_platform
Qwen-72b-chat is now on Poe, thanks to
@FireworksAI_HQ! Try it today:
Fireworks
@FireworksAI_HQ
Fireworks is committed to bringing the best model quality and performance to the community. We’ve launched the Qwen-72B model on the Fireworks platform and @poe_platform, to provide outstanding performance on English and Chinese tasks! Qwen-72B outperformed LLaMA2-70B on all tasks from benchmark datasets. Fireworks offers fast inference on Qwen with generation speeds of up to 11 ms per token generation for batch size = 1.
• Try the model directly in Fireworks’ playground (app.fireworks.ai/models/fireworks/qwen-72b-chat)
• Via API by following instructions on our docs page and using model="accounts/fireworks/models/qwen-72b-chat (readme.fireworks.ai/docs/querying-text-models)
• Via @poe_platform at poe.com/Qwen-72b-Chat
We’re excited to see what you build! -
Poe
@poe_platform
New release: Poe for Windows!
You can now get one-click access to Poe to chat with all the best LLMs, explore millions of user-created bots, and create your own, right from your Windows desktop. (1/2)
Poe
@poe_platform
You can download Poe for Windows at poe.com/download.
As usual, all bots from across Poe are available, including GPT-4, Gemini Pro, Claude 2, Claude Instant, DALL-E 3, StableDiffusionXL, Llama-2, PaLM, and all user-created bots. (2/2) -
Poe
@poe_platform
Gemini Pro is now available for all users on Poe!
This is the first official model on Poe with vision capabilities for image and video input. (Note: Video input is currently limited to web, macOS, and Windows) (1/3)
Poe
@poe_platform
Internal performance evaluations from Google have shown significant improvements for Gemini Pro over previous Google models in understanding, summarization, reasoning, coding, and planning. This model also excels in cross-modal reasoning. (2/3)
Poe
@poe_platform
The Gemini Pro bot currently supports text, image and video input with text output. We will introduce additional multimodal support in the near future.
You can try it now at poe.com/Gemini-Pro and across Poe apps on all platforms. Enjoy! (3/3) -
Poe
@poe_platform
We’ve added a new “For You” tab! This shows recommended bots based off of your usage, helping you discover new bots to try out. We’ll be working hard to improve the recommendations going forward!
-
Poe
@poe_platform
A chat-fine-tuned version of Mixtral 8x7B is now available on Poe, thanks to @thefireworksai! Try it out below:
Fireworks
@FireworksAI_HQ
Try out the new Mixtral 8x7B mixture-of-experts model fine-tuned by @thefireworksai for chat on @poe_platform! poe.com/Mixtral-8x7B-Chat
-
Poe
@poe_platform
New on Android: You can now set your default bot on Poe to any of the bots in your list. Visit the settings page and select your preferred bot to set it as your default.
We’re also rolling out a retry button, enabling you to regenerate results from any bot with one click. -
Poe
@poe_platform
Playground v2 is now available on Poe!
A powerful new graphics model that delivers diverse, high-quality imagery, Playground v2’s focus on aesthetic quality and precise image-text alignment enables you to create cutting-edge visuals with impressive accuracy.
Poe
@poe_platform
You can learn more about Playground v2 and their findings on user preference and aesthetic benchmarks here:
Suhail
@Suhail
1/ Introducing Playground v2: A new commercially open model from our team that we trained from scratch.
Most notably our model was preferred 2.5x more than the current leading open model (SDXL).
We're excited to give back to the community as we're just getting started.
Poe
@poe_platform
Try Playground v2 today on Poe: poe.com/Playground-v2
-
Poe
@poe_platform
Great example of a creative server bot on Poe:
Fireworks
@FireworksAI_HQ
Introducing the CreativeQR bot on @poe_platform, powered by @thefireworksai image generation! Generate beautiful images with scannable QR codes seamlessly embedded. Try it now at poe.com/CreativeQR
-
Poe
@poe_platform
Android users: You can now create bots on Poe!
Build no-code bots on top of the leading models, including GPT-4, Claude 2, DALL·E 3, SDXL, and Llama 2, and share them with the world. -
Poe
@poe_platform
Earlier this month, we partnered with @agihouse_org for a bot hackathon to kick off our new creator monetization program.
We were inspired by the incredible work from all of the developers and picking the top 3 was hard - but we’re excited to highlight the winning bots: (1/5)Post not available here, view on X
Poe
@poe_platform
3rd place: Fireworks-SSD-1B by James Reed poe.com/fireworks-SSD-1B
Using controlnet, this image generating bot enables users to create and transform images with impressive consistency, something that has been tough to achieve with traditional image generation models. (4/5)
Poe
@poe_platform
We’re incredibly thankful for all of the developers who participated, and every creator on Poe. You are the heartbeat of the platform and help shape the experience for millions with your work, and we’re excited to see what more folks build and earn from building on Poe. (5/5)
-
Poe
@poe_platform
Poe is now available in Traditional Chinese! Native speakers can now chat with millions of AI-powered bots and create their own bots across iOS, Android, MacOS, and Web.
-
Poe
@poe_platform
Now available: Voice input for Android 🗣️ Use your voice to ask questions, send prompts, and get answers from a wide variety of powerful and engaging bots on Poe!
-
Poe
@poe_platform
Introducing knowledge bases for Poe bots! Starting today, bot creators can now add knowledge bases to their bots, to create more unique experiences grounded in any sources they provide, complete with citations. (1/5)
Post not available here, view on X
Poe
@poe_platform
Here is an example of a knowledge base in action: poe.com/AskAboutReact This bot uses the React documentation to provide verifiable answers to questions about React development. (4/5)
Poe
@poe_platform
You can start using knowledge bases in any existing or new prompt bot today. (Note: creation of knowledge bases is currently limited to web and macOS, with support for creation on iOS and Android coming very soon.) We can’t wait to see what you create! (5/5)
-
Poe
@poe_platform
We’re excited to announce that Poe is now available in seven new languages: French, German, Italian, Korean, Portuguese, Simplified Chinese, and Spanish - across iOS, Android, MacOS, and Web! (1/2)
Poe
@poe_platform
This marks a significant milestone in our mission to make AI accessible to users worldwide, regardless of language. We look forward to having more of the world use Poe to chat with a wide variety of AI-powered bots, and to create their own bots and monetize them. (2/2)
-
Poe
@poe_platform
DALL-E 3 is now available on Poe for all subscribers across iOS, Android, MacOS, and web! You can also create prompt bots and server bots using DALL-E 3, and share in Poe revenue via the creator monetization program. (1/2)
Poe
@poe_platform
DALL-E 3 is the most powerful image generation model available today. We look forward to seeing what everyone creates! Try it at poe.com/DALL-E-3 or via any of the Poe apps. (2/2)
-
Poe
@poe_platform
To celebrate the launch of Poe creator monetization, we are hosting a hackathon at AGI House next Saturday. There will be one track for prompt engineering (no code) and another for coding. The Poe team will be present and we'll have some guest speakers. Details in the next tweet!
Poe
@poe_platform
If you are in the Bay Area and are interested in joining, you can apply at the Partiful link below (click the picture): partiful.com/e/MZBOONqkgUky4jMhO3nF
-
Poe
@poe_platform
Some coverage of our new creator monetization program:
VentureBeat
@VentureBeat
Poe wants to be the App Store of conversational AI, will pay chatbot creators venturebeat.com/ai/poe-wants-to-be-the-app-store-of-conve…
-
Poe
@poe_platform
All image-generating bots on Poe are now 2.5x as fast as they were yesterday ⚡
-
Poe
@poe_platform
Introducing creator monetization for Poe!! Full thread below 👇
Adam D'Angelo
@adamdangelo
Today we are launching creator monetization for Poe! This program lets any bot creator on Poe generate revenue. This is a major step forward for the platform and is the first program of its kind, so we are very excited to see what it lets everyone create. (thread)
-
Poe
@poe_platform
You can now upload files on Poe for Android, along with all other platforms. This enables summarization and Q&A with long documents using bots with long context windows like Claude-2-100K, Claude-instant-100K, Chat GPT-16K and GPT-4-32K.
Poe
@poe_platform
You can also share a conversation that includes a file upload with another user, which will allow them to ask questions using that file as context. Enjoy!
-
Poe reposted
Fireworks
@FireworksAI_HQ
We are excited to announce new updates available on the Fireworks Mistral-7B Poe Bot:
1/ Sliding Window Attention - process sequences up to 32K efficiently thanks to sliding window optimization.
2/ Proper BOS Handling - Mistral-instruct now follows the conversation template it was originally trained with, including the system prompt. This update follows the recent information released by the Mistral team.
3/ Repetition Penalty Support - the model now supports a repetition penalty to reduce the likelihood of generating repetitive sequences of tokens.
Try it here: poe.com/fw-mistral-7b -
Poe reposted
Heather Cooper
@HBCoop_
🖼You can generate images with StableDiffusionXL on @poe_platform and build your own image-generating bot, using SDXL 👇
Poe
@poe_platform
New today: StableDiffusionXL is now available on Poe! This image generation model is capable of turning prompts into high quality, expressive images within seconds. And unique to Poe, you can build bots on top of it (more about this later in this thread). (1/7)
-
Poe
@poe_platform
New today on Android: Search for specific bots or users! This is available from the top of the Explore bots page. We also updated the landing page to allow fast access to the top bots in each category.
-
Poe
@poe_platform
Poe subscriptions are now available in Mexico and Brazil! Subscribing gives you access to powerful models like GPT-4 and Claude-2 and any user-created bots built on them, higher message limits, and faster response times. You can subscribe on iOS, Android, MacOS, or the web.
-
Poe
@poe_platform
Last weekend we hosted an online hackathon with developers from around the world. We are excited to announce the winners of the top 3 prizes:
Post not available here, view on X
Poe
@poe_platform
3rd place is The Illusionist by AM. This helps you generate images that follow a spiral pattern or any other pattern you give it. poe.com/TheIllusionist
Poe
@poe_platform
We really appreciate everyone's participation, and were inspired by the ideas we saw among the bots we could not give prizes to. We also learned a lot that we will incorporate into improving the platform going forward. Stay connected for updates on future hackathons!
-
Poe
@poe_platform
New today: we added a resend button on web and iOS for SDXL and SDXL-based bots! Clicking resend will preserve the previous image and add a second generation from the model, so you don't have to copy and paste a prompt multiple times.
-
Poe
@poe_platform
How do the top LLMs compare? We partnered with @SurgeAI for a systematic evaluation of each across four attributes: Reasoning, Writing, Creativity, and Non-English Fluency, and the results are in 👇 (1/7)
Post not available here, view on X
Poe
@poe_platform
And of course, Poe provides access to any of these official bots from OpenAI, Anthropic, Google, or Meta, along with millions of user-created bots built on top of them (7/7).
Poe
@poe_platform
Addendum: corrected link to Surge AI: @hellosurgeai!
-
Poe
@poe_platform
New today: You can now subscribe to Poe within the Android app! Subscribing provides access to GPT-4 (including 32k), Claude 2, and all user-created bots that use them as a base. Subscriptions work across platforms, so if you subscribe on Android you can use your access anywhere.
-
Poe reposted
Adam D'Angelo
@adamdangelo
Excited for this tomorrow, and will include some new details about our plans for developers.
-
Poe
@poe_platform
We’re celebrating the release of the Poe API v2 with a virtual hackathon this Saturday. All developers are welcome and we have a 10k prize pool!
-
Poe
@poe_platform
Mistral 7B is now available on Poe! Thanks to our API launch yesterday, Fireworks was able to quickly make this model available for all Poe users across the iOS, Android, web, and MacOS apps:
Fireworks
@FireworksAI_HQ
Fireworks blazing fast LLM inference is now available on Poe!
Today, we’re excited to bring the power of the new Mistral 7B Instruct model to the @poe_platform powered by our lightning-fast Fireworks inference platform.
You can now have conversations with the Mistral 7B bot and even build your own bots on top of it.
Try it here: poe.com/fw-mistral-7b -
Poe reposted
Kshitij Grover
@kshithappens
This is fascinating— poe lets you build server bots that query other models— like Claude Instant or GPT 3.5— *for free*.
Making new bots easy comes with an important realization: it’s not just devex— it’s also cloud economics.
Adam D'Angelo
@adamdangelo
Introducing the Poe API v2! This uniquely lets any bot on Poe query any other bot for free and use the output as input. Developers do not have to pay for this; instead the queries are covered under the *user's* normal message allocation on Poe.
-
Poe
@poe_platform
Introducing the Poe API v2 for developers! First, this now lets any bot on Poe to query any other bot for free and use the output as input. Developers do not have to pay anything for this; any messages used are covered under users' normal free messages on Poe. (thread)
Post not available here, view on X
Poe
@poe_platform
These launches today are an important step toward our goal to make Poe the easiest way to build a chat-based AI product and get it to a mass audience. We have a few more key features for developers we will be launching soon to continue to unlock the potential of the platform.
Poe
@poe_platform
If you are interested in building a bot, you can see our documentation at developer.poe.com. We’re excited to see what everyone builds on top of this and will continue to do our best to support all of you!
-
Poe
@poe_platform
Some great image generating bots are being created on SDXL:
Windy Island Games
@games_windy
Created a second bot @poe_platform for more generic 'Black and White Comic Book art' named 'ComicBook_BW_781'.
Prompt for testing : A chopper rider on the highway
#synthography #aiart #aiartwork #aiartcommunity #sdxl #stablediffusion #promptshare
poe.com/ComicBook_BW_781 -
Poe
@poe_platform
New today: we added a retry button on web and iOS! One click to regenerate any result from any bot!
-
Poe
@poe_platform
New today: StableDiffusionXL is now available on Poe! This image generation model is capable of turning prompts into high quality, expressive images within seconds. And unique to Poe, you can build bots on top of it (more about this later in this thread). (1/7)
Poe
@poe_platform
You can access the model directly at poe.com/StableDiffusionXL or via the Poe app on iOS, Android, or macOS. (2/7)
Poe
@poe_platform
We are especially excited about providing everyone the ability to create custom prompt bots based on StableDiffusionXL. Use your own prompts to infuse specific styles or elements into your custom image generation bots, and you can then share those bots with others. (3/7)
Post not available here, view on X
Poe
@poe_platform
We’re looking forward to seeing what everyone creates with these new capabilities! And finally, similar to the Web Search bot we launched yesterday, the StableDiffusionXL bot is built entirely on the same Poe API that is available to all developers. (6/7)
Poe
@poe_platform
We are making sure we build all these bots on our own API to ensure it is robust and first class as we prepare for some major new features for developers soon! (7/7)
-
Poe
@poe_platform
Today we are excited to introduce a new bot on Poe: Web Search! This general-purpose bot is capable of conducting web searches as necessary to inform its responses, making it particularly good for queries requiring the latest information or specific facts. (1/5)
Post not available here, view on X
Poe
@poe_platform
Additionally, we are excited to share that as part of our work to make the Poe API for developers robust and first class, we built this Web Search bot entirely on the Poe API, using the same interfaces that any external developer can build on top of. (4/5)
Poe
@poe_platform
We are working hard to bring even more power to developers and will have more to announce regarding the API soon. In the meantime, you can get started building bots at developer.poe.com/server-bots/quick-start ! (5/5)
-
Poe
@poe_platform
We just rolled out two new features on Poe for Android. First is the ability to filter bots by category on the explore page. Second is the ability to manually toggle between dark and light mode, on the settings page. These are available on the latest version of the app today!
-
Poe
@poe_platform
The newly-released gpt-3.5-turbo-instruct model from OpenAI is now available on Poe! This is an InstructGPT 3.5 class model, fine tuned for instruction following, and many people are finding it performs very well for specific tasks (e.g. playing chess at Elo 1800)
Poe
@poe_platform
You can try it at: poe.com/GPT-3.5-Turbo-Instruct . Enjoy!
-
Poe
@poe_platform
Check out the CreatePlaylist bot, just built on the Poe API:
Poe
@poe_platform
You can try it yourself at: poe.com/CreatePlaylist
-
Poe
@poe_platform
Solar, a new bot created by Upstage, is now available on Poe. As a top-ranked model on the HuggingFace Open LLM leaderboard, and a fine tune of Llama 2, Solar is a great example of the progress enabled by open source. (1/3)
Poe
@poe_platform
We are looking forward to providing access to more models. If you are experimenting with fine tuning Llama 2 or any other model, it’s easy to use Poe as a frontend via our API: developer.poe.com/api-bots/quick-start. And feel free to contact us at developers@poe.com with more questions. (2/3)
Poe
@poe_platform
You can try Solar at poe.com/Solar-0-70b ! (3/3)
-
Poe
@poe_platform
A recap of some of our recent launches: www.theverge.com/2023/8/28/23849161/poe-ai-chatbot-platfo…
-
Poe
@poe_platform
Just launched: screenshot sharing on Poe for iOS. From the share feature, choose "Share privately", and then use "Share screenshot" instead of "Share link." Screenshots can be more convenient for sharing on social media or messaging apps than links!
-
Poe
@poe_platform
You can now create custom prompt bots on Poe based on Llama 2! This feature is available on iOS, macOS, and Web via "Create bot" on the left hand menu, and is coming soon on Android. (1/2)
Poe
@poe_platform
If you're creating a bot, this option gives you more flexibility in case the other models don't meet your needs. And since Llama 2 is open source, you don't have to worry about your bot changing behavior or the base model going away in the long term. (2/2)
-
Poe
@poe_platform
Code Llama is now available on Poe! Note that many of the Code Llama demos floating around during the last week on other services had bugs; we took some time to make sure our implementation works accurately to the underlying model.
Poe
@poe_platform
This model excels at generating and understanding code. You can find the bot at poe.com/Code-Llama-34b . Enjoy!
-
Poe
@poe_platform
Today we upgraded Google-PaLM on Poe to a significantly improved version of the model! The model has progressed in summarization, creativity, reasoning, coding, conversation, and many other categories. In addition, its responses are more coherent and natural sounding.
Poe
@poe_platform
You can access the model at poe.com/Google-PaLM or via the Poe app on iOS, Android, or macOS.
-
Poe reposted
Charly Wargnier ♨️
@DataChaz
The new Poe (@poe_platform) is jam-packed with updates! 🤯
1. Threading: Organized separate chat conversations
2. Bot search: Search bots+people
3. Now w/ @Meta's #llama2
4. Adjust bot creativity w/ custom temperature
5. Poe for Mac
6. Poe in Japanese 🇯🇵
#llms #generativeai -
Poe
@poe_platform
New: bot search! We are very excited to add the ability to search for bots on Poe on iOS, web, and MacOS today! You can search for specific bots or discover new ones tailored to your interests. This feature is coming soon on Android. (1/2)
Poe
@poe_platform
Search is available at the top of the Explore page. You can also search for people using the tab at the top of the search results. If you are on iOS you may need to upgrade to the latest version. Please send all feedback to feedback@poe.com . Thank you for your patience! (2/2)
-
Poe reposted
Hiten Shah
@hnshah
Another multi-hour session working with Claude and ChatGPT. Used @poe_platform to switch between the models while working on some product and marketing things. I’m ready for that prompt engineering job now 🤣
-
Poe
@poe_platform
New on Poe today: threading! Your conversations on Poe will now be organized into separate chats. This lets you easily have multiple conversations going with the same bot at the same time, or pick up a previous conversation where you left off. (1/2)
Poe
@poe_platform
Threading works across all bots on Poe and all platforms: iOS, Android, Web, and MacOS. This is a big launch that sets us up for some other important features we will be working on next. Please share all feedback with us at feedback@poe.com . Thank you! (2/2)
-
Poe
@poe_platform
New: Claude-instant and Claude-instant-100k on Poe are now powered by @AnthropicAI's Claude Instant v1.2. This model represents a substantial improvement over the previous iteration across multiple domains, particularly in reasoning and code.
-
Poe
@poe_platform
We are excited to add three new bots based on Llama 2: Llama-2-70b, Llama-2-13b, and Llama-2-7b. Our recommendation is to use 70b, as it provides the highest quality responses. It is significantly better than the 7b and 13b models that many people have been testing the last week.
Post not available here, view on X
Poe
@poe_platform
We are especially looking forward to providing access to fine-tuned versions of Llama as the community creates those. If you are experimenting with fine tuning Llama or any other model, it’s easy to use Poe as a frontend for your model via our API: developer.poe.com/api-bots/quick-start
Poe
@poe_platform
We are also interested in helping host fine-tuned versions of Llama so that developers don’t have to manage a server or pay large costs if their bot gets popular. Please reach out to us at developers@poe.com if you are interested in participating in this program.
-
Poe
@poe_platform
We are very excited to launch Poe in Japanese on iOS, Android, MacOS, and web today. We look forward to having more Japanese speakers use Poe to chat with a wide variety of AI-powered bots, or to create their own bots. (1/3)
Poe
@poe_platform
If you speak Japanese, please follow @poe_platformjp for future updates! (2/3)
Poe 日本語版
@poe_platformjp
ついに高速AIチャット「Poe」が日本語でも利用できるようになりました! 詳細はこちらをご覧ください ▼
quorajp.quora.com/Poeが日本語でも利用できるようになりました
Poe
@poe_platform
While Japanese is our first language for Poe outside of English, we are committed to providing access to Poe in other languages over the coming months. To try Poe in Japanese, visit the iOS app store, Google Play Store, or try Poe at poe.com. (3/3)
-
Poe
@poe_platform
You can now set a custom temperature on prompt bots on Poe! Read on for more details about the change in this thread:
Poe
@poe_platform
Temperature allows you to make a bot more consistent, to the point where it will be close to deterministic with temperature=0, or more creative and unpredictable with higher temperatures.
Poe
@poe_platform
Note that even temperature 0 will not be 100% deterministic, but it should be very close:
Boris Power
@BorisMPower
This happens with all the models in our API when there’s a tiny difference (<1%) in probability between the two top tokens, due to non determinism.
Once you get one different token then the completions might start to diverge more
Poe
@poe_platform
Also remember that in addition to prompt bots (which this change applies to), we also allow anyone to create an API bot, which allows unlimited control over bot output: developer.poe.com/api-bots/quick-start
Poe
@poe_platform
There are now hundreds of thousands of bots on Poe, and you can see some of them at poe.com/explore_bots . We are continuing to invest heavily in improving the bot creator experience so please share all feedback to feedback@poe.com. Thank you!
-
Poe
@poe_platform
You can now drag and drop files into the input window on web to upload them. File uploading on bots with longer context windows makes it possible to summarize long documents quickly. And share allows other users to continue the conversation with the context of the file.
-
Poe
@poe_platform
Going forward, Sage will be called Assistant on Poe, accessible from the left hand menu. Assistant can help you with a wide variety of tasks and is available across iOS, Android, web, and our Mac desktop app. It is powered by the same GPT-3.5 model as ChatGPT.
-
Poe
@poe_platform
Some summaries of the senate UFO bill by Schumer: first from Claude 2:
Poe
@poe_platform
And second from GPT-4-32k:
Poe
@poe_platform
Continue either conversation: Claude 2: poe.com/s/x8lvyyxkX0mPzQbSPIJA and GPT-4: poe.com/s/FFDSJLsQIsNGLU3Gdm00
-
Poe
@poe_platform
Today we are releasing the first version of Poe for Mac! You can download it for one-click access to Poe from your system dock, and a global hotkey (⌘-/) to open Poe from anywhere. Download link in next tweet in this thread.
Poe
@poe_platform
You can download it from poe.com/download . As usual, all bots from across Poe are available, including ChatGPT, GPT-4, Claude 2, Claude Instant, PaLM, and all user-created bots. All your conversations from Poe on all other platforms will sync to Poe on Mac.
Poe
@poe_platform
Please share all feedback with us at feedback@poe.com.
-
Poe reposted
Adam D'Angelo
@adamdangelo
A cool thing you can do with the features we launched today: upload a file and then share the conversation so others can ask questions of the AI about it. For example, here's today's court decision about the FTC vs. Microsoft + Activision Blizzard:
-
Poe
@poe_platform
Today we are launching new, more powerful models with increased context windows on Poe, including the just-released Claude 2 with its 100k-token window length, along with a set of new tools to help everyone take advantage of them. (thread below)
Post not available here, view on X
Poe
@poe_platform
In order to address this bottleneck, we are launching a set of new features which augment human input: file uploading, URL retrieval, and continue chat.
Poe
@poe_platform
File uploading, available on web and mobile web, allows anyone to take a file and add it to a message on Poe. We process the file to extract the text and show the contents directly to the model as part of the conversation.
Post not available here, view on X
Poe
@poe_platform
As always, all models on Poe are available on all platforms: our web and mobile web product at poe.com, and our native iOS and Android applications.
Poe
@poe_platform
Please send all feedback to feedback@poe.com. This is a large release and so we will especially appreciate any bug reports. We will be working hard to fill in support for file uploading and continue chat on iOS and Android soon. Thank you!
-
Poe
@poe_platform
Today we are launching a set of features on Android that are currently available on iOS and web. You can now create and see your profile, accessible from the left hand menu. You can also remove bots from your bot list, accessible by tapping the bot name at the top of the chat.
Poe
@poe_platform
We have also added the stop button on Android, so you can cut off any bot response without waiting for it to finish. Please share any feedback to feedback@poe.com. Thank you!
-
Poe
@poe_platform
We are excited to announce that Google's PaLM 2 is now available on Poe! You can find it in the left sidebar, or in the "all your bots" menu, or at poe.com/Google-PaLM
-
Poe reposted
WeirdMomma 🥓⁉️
@weird_momma_x
The Claude-instant-100k bot really is the best brainstorming partner. I highly suggest paying for the @poe_platform sub to have access. I'm not paid to say this. Just very enthusiastic
poe.com -
Poe
@poe_platform
New: you can now set your default bot on Poe to any of the bots in your list! This is done via the settings page, and will sync across iOS and web, and will be coming soon to Android.
-
Poe
@poe_platform
Claude instant 100k: what advice does the entire text of The Prince give regarding mercenaries?
-
Poe
@poe_platform
You can now create bots on Poe using our more powerful models: Claude+ and GPT-4. Custom prompt bots on these models should perform significantly better on coding or other complex tasks, or when significantly more context is required.
Post not available here, view on X
Poe
@poe_platform
As with the base Claude+ and GPT-4 models, message sending for these bots will have certain limits for non-subscribers. Note these limits depend on the subscription status of the person *using* the bot, not the bot creator.
Poe
@poe_platform
Bot creation is available on iOS and web and is coming to Android soon. Please send any feedback to feedback@poe.com. We are looking forward to seeing what everyone else creates with these newly-unlocked capabilities!
-
Poe
@poe_platform
You can now remove user-created bots from your bot list, accessible by tapping the bot name at the top of the chat.
Poe
@poe_platform
This feature is available on web and iOS, and is coming soon to Android. If you're on iOS and don't see it yet, you may need to upgrade to the latest version in the App Store.
-
Poe
@poe_platform
Just launched: any bot you create on Poe can now be set to private, which will make the bot available only to you and won't display it on your profile. You can change this setting for existing bots by using "Edit bot", accessible by clicking the bot's name at the top of a chat.
-
Poe
@poe_platform
Poe now has a stop button for both web and iOS, so you can cut any bot off if you want to change your request without waiting for it to finish. iOS users may need to update to the latest release in the App Store to see the feature. Android support is coming soon.
-
Poe reposted
Dr. Daniel Bender
@drdanielbender
💪🔁 AI-generated summary of the workout routine from Andrew Huberman, which was explained by him with a lot of detail in the @timferrisshow podcast episode #660
The complete transcript of the episode contains more than 33k words, and the passage where @hubermanlab explains his workout more than 10k:
tim.blog/2023/03/10/dr-andrew-huberman-transcript/
This is far too much to be summarized by the default version of GPT-4. I fiddled around a bit by splitting it but to be honest, I did not like the process and put it on my To-Do list for later.
Now, I tried it again by using the complete transcript as input in the Claude-instant-100k model on @poe_platform and asked to summarize the workout routine with the following prompt (note that this even contains an incomplete sentence):
Please summarize the complete workout routine very detailed. Describe all the exercises and what the train. Explain why Andrew Huberman is training in the specific order and what the science behind it is.
The response stopped after describing Wednesday, and I had to ask the model to continue. Besides that, the result looks good. The original responses are attached as images and the combination of both answers in text form to copy & paste it if needed👇.
And thanks to being a chatbot you can ask for explanations of terms you don't know or more details on some aspects, like a specific exercise.
---
Here is a detailed summary of Andrew Huberman's full weekly workout routine:
Sunday: Long, slow hike or jog for endurance
He goes for a 75-90 minute walk or slow jog while wearing a weighted vest.
The goal is to build endurance and improve zone 2 cardiovascular fitness.
The repetitive movement activates central pattern generators in the nervous system, making the movement more automatic and reducing the mental effort required.
Monday: Leg workout focusing on strength and hypertrophy
He starts with tibialis raises to warmup the shins and activate the tibialis anterior muscle. This helps with posture and stability throughout the leg workout.
Then he does calf raises to target the two calf muscles - gastrocnemius and soleus. Building calf strength improves push-off power and reduces pressure on the knees.
Next are leg curls to work the hamstrings since they are typically weaker than the quads. Flexing the knees brings the heels towards the glutes to contract the hamstrings.
Glute-ham raises target the entire posterior chain by mimicking a deadlift movement while lying facedown. Strengthening these muscles improves lower back health, posture and leg drives.
Leg extensions isolate the quadriceps muscles by fully extending the knees. This builds strength in the quads to balance out the hamstrings work.
Hack squats target the entire leg but focus more on the quadriceps. They allow him to load more weight for maximal strength gains.
He keeps the rest periods short to retain muscle tension and focuses on lifting as much weight as possible while maintaining good form. This builds both strength and hypertrophy.
Tuesday: Heat exposure and cold plunges
He spends 20 minutes in a hot sauna followed by 3-5 minutes in a cold plunge.
He repeats this cycle 3-5 times.
The extreme temperature changes stress the body in a beneficial way, increasing growth hormone, stimulating fat loss and improving his tolerance for heat and cold.
The heat exposure also reduces muscle soreness from the previous leg workout.
Wednesday: Cardiovascular workout
He does either a 25-30 minute run at a steady pace or a "torso" weight training workout if his legs are still sore.
The run improves his aerobic fitness and cardiovascular health while active recovery benefits muscle repair.
The torso workout consists of exercises that target the chest, shoulders and back muscles using push and pull movements. This includes overhead shoulder presses, dips, chin ups, etc. This mitigates muscle imbalances from focusing on lower body training earlier in the week.
Thursday: Same as Wednesday
If his legs are still sore, he does the torso workout from Wednesday to focus on upper body.
Otherwise, he does the 25-30 minute run from Wednesday to improve his cardiovascular fitness.
Friday: High-intensity interval training
He does a short workout like sprints on an assault bike or jump training to elevate his heart rate and improve his VO2 max.
The emphasis is on quick, explosive movements to recruit fast-twitch muscle fibers and build power.
This workout also indirectly stresses the leg muscles to help maintain hypertrophy gains from earlier in the week.
Saturday: Focus on smaller muscle groups
He targets minor muscle groups like biceps, triceps and rear deltoids.
This consists of exercises like preacher curls, tricep extensions, and rear delt flyes.
He also does another tibialis and calf workout to keep those muscles primed.
The focus is more aesthetic on Saturday to balance out the major compound movements earlier in the week.
In summary, Andrew trains each muscle group with the appropriate volume, intensity and exercises to trigger different muscle adaptations - endurance, strength, size and power - while allowing for adequate recovery in between. The key is maintaining a balance of workouts that challenges the whole body in multiple ways. -
Poe reposted
Rachel Woods
@rachel_l_woods
I'm a little obsessed with the @poe_platform Midjourney Bot. Takes basic prompts and adds the ✨ magic ✨
A little bit on how it works: -
Poe reposted
Valentin
@vmuaddib
that feeling when you nail the perfect prompt ✨. Nothing beats @AnthropicAI 100k tokens, even on instant, via @poe_platform
-
Poe
@poe_platform
Today we are launching a set of recently-enabled web features on Poe for iOS, including manual control over dark/light mode and exploration of user-created bots. You can access these new features by updating your Poe iOS app to v1.2.13.
Poe
@poe_platform
The explore bots feature is available from the left hand menu. From there, you can find a wide variety of bots to try, including ones that are useful for advice like PythonMachine or Leocooks, or bots to have fun with like RolePlayGameBot or RoastMaster. poe.com/leocooks
Poe
@poe_platform
You can toggle between dark and light mode on the settings page, accessible from the left hand menu. Please share any feedback with us and we will continue to work on improving the experience of Poe for iOS and across all platforms!
-
Poe reposted
Tim Hwang
@timhwang
steve jobs, 1983
-
Poe
@poe_platform
We just launched voice input for all bots on Poe for web. iOS and Android are coming soon!
-
Poe
@poe_platform
Introducing Poe for Android! Poe is the easiest and fastest way to chat with AI including ChatGPT, Anthropic’s Claude instant, and a variety of user-created bots for free.
-
Poe
@poe_platform
100k context windows now available on Poe: we are excited to start a beta test for Claude-instant-100k! This bot is currently available to all Poe subscribers, initially on web only. It can understand message history as long as a 200 page book. Examples in thread below.
-
Poe
@poe_platform
Today we are launching a way to explore user-created bots on Poe on web. In the last month, over 100,000 bots have been created on Poe through prompts. You can click on “explore bots” on the left hand menu to access it!
-
Poe
@poe_platform
Android work in progress
-
Poe
@poe_platform
Today we are launching Poe subscriptions on web, which gives paying users the ability to talk to both GPT-4 and Claude+. Subscribing on web or iOS gives you seamless use of these bots across all platforms. Subscriptions were previously only available on iOS.
-
Poe
@poe_platform
We just launched markdown code block improvements on web including syntax highlighting and a copy button! These improvements apply across all bots on Poe, including ChatGPT, Claude instant, Claude+, GPT-4, and all user-created and API bots.
-
Poe
@poe_platform
We are excited to launch @Neeva's NeevaAI bot on Poe today. NeevaAI cites sources and includes up to date information in its replies. It is a much easier way to get a synthesized answer from an internet search.
-
Poe
@poe_platform
Claude+ on Poe is now powered by @AnthropicAI's new Claude-v1.3. Claude+ now produces better quality code, has better support for Markdown, and should generally produce higher quality answers. You can access it at poe.com/claude+ or via the Poe app in the iOS App Store.
-
Poe
@poe_platform
We just launched Claude instant, a new free, faster model replacing Claude, at poe.com/claude-instant. Claude instant will be better than the previous Claude model in some cases and worse in other cases. For the highest quality experience, Claude+ is available to subscribers.
-
Poe
@poe_platform
ChatGPT is now available as a bot on Poe! Accessible via the menu in the top left:
-
Poe
@poe_platform
-
Poe
@poe_platform
We're starting this new account to share updates and highlights about Poe! See more details here:
Adam D'Angelo
@adamdangelo
Today, we are opening up public access to a new AI product we have been building called Poe. Poe lets people ask questions, get instant answers, and have back-and-forth conversations with several AI-powered bots. (1/n)













































































































































































































































































































































































