6d ago · 25 min read · TLDR: Chain of Thought (CoT) prompting tells a language model to reason out loud before answering. By generating intermediate steps, the model steers itself toward correct conclusions — turning guesswork into structured reasoning. It's the difference...
Join discussion
Apr 17 · 4 min read · Two things happened in AI research this week, and they point in opposite directions. Inference got meaningfully faster. And several papers made it clearer than ever exactly where reasoning models break, no matter how fast you run them. Start with the...
Join discussion
Apr 10 · 5 min read · There is a version of the superintelligence story where a researcher has a conceptual breakthrough, some fundamental insight about cognition that nobody else has seen, and the world changes overnight. Good fiction. I've written some of it myself. I t...
Join discussionApr 10 · 6 min read · Does tree search help LLM reasoning? The literature can't decide. ReST-MCTS* says yes. AB-MCTS got a NeurIPS spotlight. "Limits of PRM-Guided Tree Search" says no: MCTS with a process reward model used 11x more tokens than best-of-N for zero accuracy...
Join discussionApr 8 · 3 min read · Z.ai just released GLM-5.1, a 754 billion parameter model from the Chinese AI lab, and something unusual happened when Simon Willison ran the standard pelican test. The model didnt just generate an SVG of a pelican on a bicycle. It spontaneously crea...
Join discussionFeb 12 · 2 min read · RynnBrain, an initiative from Alibaba's DAMO Academy, introduces open embodied foundation models aimed at enhancing artificial intelligence capabilities in reasoning and interaction. This project underscores a shift towards developing AI that can eng...
Join discussionFeb 11 · 2 min read · RynnBrain, an initiative from Alibaba's DAMO Academy, introduces open embodied foundation models aimed at enhancing artificial intelligence capabilities in reasoning and interaction. This project underscores a shift towards developing AI that can eng...
Join discussionJan 16 · 5 min read · Large language models feel impressive right up until they do not. The responses still look fluent. The structure still appears logical. But somewhere beneath the surface, reasoning quality drops. Assumptions blur. Constraints leak. The model keeps ta...
Join discussionDec 18, 2025 · 6 min read · Every developer has a "long context" horror story. It usually starts the same way. You see a model announcement claiming a 100k, 200k, or even a million-token context window. You get excited. You think, finally, I can dump my entire codebase, three y...
Join discussion
