ChatGPT needs a 'fork chat' feature. I want to be able to branch a conversation from any point like git branch -> explore alternate timelines without ruining the main thread. or copy pasting like a freak

We took over a former technical university. This is Hogwarts in real life. For people who want to work on something too early, too weird, too ambitious.

introducing Egocentric-1M. the largest egocentric video dataset in the world, and our next step in building the internet for physical AI.

As a fun Saturday vibe code project and following up on this tweet earlier, I hacked up an **llm-council** web app. It looks exactly like ChatGPT except each user query is 1) dispatched to multiple models on your council using OpenRouter, e.g. currently: "openai/gpt-5.1", "google/gemini-3-pro-preview", "anthropic/claude-sonnet-4.5", "x-ai/grok-4", Then 2) all models get to see each other's (anonymized) responses and they review and rank them, and then 3) a "Chairman LLM" gets all of that as context and produces the final response. It's interesting to see the results from multiple models side by side on the same query, and even more amusingly, to read through their evaluation and ranking of each other's responses. Quite often, the models are surprisingly willing to select another LLM's response as superior to their own, making this an interesting model evaluation strategy more generally. For example, reading book chapters together with my LLM Council today, the models consistently praise GPT 5.1 as the best and most insightful model, and consistently select Claude as the worst model, with the other models floating in between. But I'm not 100% convinced this aligns with my own qualitative assessment. For example, qualitatively I find GPT 5.1 a little too wordy and sprawled and Gemini 3 a bit more condensed and processed. Claude is too terse in this domain. That said, there's probably a whole design space of the data flow of your LLM council. The construction of LLM ensembles seems under-explored. I pushed the vibe coded app to github.com/karpathy/llm-coun… if others would like to play. ty nano banana pro for fun header image for the repo

wrote a blog post after a long time your agent doesn't need better retrieval. it needs to remember you. new post on memory vs rag

current chat interfaces suck, so i built a canvas for llms

🚀Introducing Code Arena: the next generation of live coding evals for frontier AI models. Built to test how models plan, scaffold, debug, and build real web apps step-by-step. Try Claude, GPT-5, GLM-4.6 and Gemini in Code Arena today!

why nobody puts a dark toggle in the settings? 🥲love that you can drag them around also :D

Chat interfaces suck. So this guy literally built a canvas for LLMs. Forget linear ChatGPT. With this app now you can branch, parallelize, and collaborate like Git Figma for AI! 🤯 App link below ↓

current chat interfaces suck, so i built a canvas for llms

fastest company to $100m arr or jail

if its powered by the x api it costs a ton

By popular request: you can now branch conversations in ChatGPT, letting you more easily explore different directions without losing your original thread. Available now to logged-in users on web.