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) Some examples:
• BigBrainTeacher (below) creates comedic educational videos: poe.com/Big-Brain-Teac…
• PixelGIFGenerator makes custom animated GIFs: poe.com/Pixel-GIF-Gene…
• AIQuartet calls the top LLMs to brainstorm any task: poe.com/AIQuartet (2/9)

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 🧵 With one API key, you get access to all models on Poe, including ones from OpenAI, Anthropic, Google, xAI, and more - plus millions of custom bots created by our community. This allows you to switch between o3, Grok 4, or any other model with a single parameter change. (2/7)

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) Previews can be shared with anyone via a dedicated link, and you can view your output in a new tab outside the chat. You can also leverage Poe features like multi-bot chat, file upload, and video input to help you build your custom web applications. (2/5)

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) GPT4 wins the competition on all dimensions (not counting speed and price) but there are some notable callouts in 2nd place. (2/7)

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) This matters because developing a free product based on an LLM is risky: if it goes viral, you will either hit your account limit and the bot will go down, or if you raise your limit you will be hit with a prohibitively expensive bill from your LLM provider.

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) As AI gets more powerful, the bottleneck in human-AI collaboration can become the input channel between the human and the AI, rather than the capabilities of the AI itself. This bottleneck can get especially severe with longer context windows.

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. You can use it to ask for summaries, to continue writing in long documents, to follow instructions in a manual, or anything else you’d like. Here it is writing an epilogue for entirety of The Great Gatsby: