1. C Check out our latest SAIL blog post on TRACER! This multimodal system uses bedside video and EHRs to... Check out our latest SAIL blog post on TRACER! This multimodal system uses bedside video and EHRs to help clinicians understand how patient behavior changes over a hospital stay: a 10/17 03:03 ♡
2. W Work advised by @simran_s_arora @Azaliamirh @HazyResearch. Work advised by @simran_s_arora @Azaliamirh @HazyResearch . 💬 0 🔄 0 ❤️ 6 👀 1821 📊 1 ⚡ Powered by xgo.ing 10/16 05:59 ♡
3. What if language models wrote the way that we think through ideas: rough sketch first with details l... What if language models wrote the way that we think through ideas: rough sketch first with details last? New work by @KumbongHermann , @ishanskhare , and team introduces Next-Conce 10/16 05:59 ♡
4. What if language models wrote the way that we think through ideas: rough sketch first with details l... What if language models wrote the way that we think through ideas: rough sketch first with details last? New work by @KumbongHermann , @ishanskhare , and team introduces Next-Conce 10/15 07:45 ♡
5. W Work advised by @simran_s_arora @Azaliamirh @HazyResearch Work advised by @simran_s_arora @Azaliamirh @HazyResearch 💬 0 🔄 0 ❤️ 5 👀 2046 📊 1 ⚡ Powered by xgo.ing 10/15 07:45 ♡
6. C Check out our latest SAIL blog post on CausalSmith! This agentic framework automates theoretical cau... Check out our latest SAIL blog post on CausalSmith! This agentic framework automates theoretical causal inference research, using Lean to verify proofs and an audit step to make su 10/15 06:50 ♡
7. C Can a robot learn dexterous manipulation from just one human video? Check out our latest SAIL blog p... Can a robot learn dexterous manipulation from just one human video? Check out our latest SAIL blog post on DexAgent, an agentic framework that turns a single egocentric video into 10/15 06:45 ♡
8. S Stanford AI Lab is alive and well at COLM! Check out these SAIL projects this week in SF. 🎉 https... Stanford AI Lab is alive and well at COLM! Check out these SAIL projects this week in SF. 🎉 ai.stanford.edu/blog/colm-2026/ m 💬 3 🔄 5 ❤️ 40 👀 10355 10/08 01:43 ♡
9. SWE-chat by @joabaum is a living dataset of human interactions with AI coding agents. 230K prompts f... SWE-chat by @joabaum is a living dataset of human interactions with AI coding agents. 230K prompts from real developers collected in the wild are now available on HuggingFace  10/03 03:00 ♡
10. Some interesting and perhaps unexpected properties of tokenization for language models! Some interesting and perhaps unexpected properties of tokenization for language models! Rylan Schaeffer @RylanSchaeffer Tokenizer Myths and Where to Find Them! Slides from talk las 10/03 02:17 ♡
