How do LLMs learn to reason from data? Are they ~retrieving the answers from parametric knowledge🦜? In our new preprint, we look at the pretraining data and find evidence against this:. Procedural knowledge in pretraining drives LLM reasoning ⚙️🔢. 🧵⬇️

RT @RTomMcCoy: 🤖🧠 NEW PAPER ON COGSCI & AI 🧠🤖. Recent neural networks capture properties long thought to require symbols: compositionality,….

Join millions who have switched to Grok.

RT @EkdeepL: I am not leaving academia though! I'll be applying for academic jobs this fall. My primary motivation to join @GoodfireAI in t….

RT @EkdeepL: Super excited to be joining @GoodfireAI! I'll be scaling up the line of work our group started at Harvard: making predictive a….

RT @zhengyaojiang: Quick takes on GPT-5 on MLE-Bench:. - It's not based on the full set or the lite set but rather the "30 most interesting….

RT @NeelRajani_: Yesterday, OpenAI released an open LLM for the first time since 2019! They co-released a paper on malicious fine-tuning to….

RT @_rockt: Harder, Better, Faster, Stronger, Real-time! We are excited to reveal Genie 3, our most capable real-time foundational world mo….

RT @TheOneKloud: Excited to reveal what I've been working on for the last few months. Command-A-Vision is our new flagship 112B VLM that ou….

RT @zhengyaojiang: Thrilled to announce Weco has raised an $8M seed led by @GoldenVentures to build self-evolving software!. Our technology….

RT @j_foerst: 🚨job alert🚨@FLAIR_Ox is looking for a postdoc, deadline is 1st of September (. By many reports we are….

RT @scychan_brains: Before money, human societies tended to use credit/debit (and minimal bartering). But most ended up developing money 💵….

RT @robertarail: I’m building a new team at @GoogleDeepMind to work on Open-Ended Discovery!. We’re looking for strong Research Scientists….

RT @NeelRajani_: 🚨New paper alert!🚨. "Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them" @ActInterp ICML'25. @dee….

RT @sarahwiegreffe: A bit late to announce, but I’m excited to share that I'll be starting as an assistant professor at the University of M….

RT @PaglieriDavide: LLMs acing math olympiads? Cute. But BALROG is where agents fight dragons (and actual Balrogs)🐉😈. And today, Grok-4 (@….

RT @egrefen: Do you have a PhD (or equivalent) or will have one in the coming months (i.e. 2-3 months away from graduating)? Do you want to….

RT @hannahrosekirk: My team at @AISecurityInst is hiring! This is an awesome opportunity to get involved with cutting-edge scientific resea….

RT @KobiHackenburg: Today (w/ @UniofOxford @Stanford @MIT @LSEnews) we’re sharing the results of the largest AI persuasion experiments to d….

RT @dmkrash: Check out my posters today if you're at ICML!.1) Detecting high-stakes interactions with activation probes — Outstanding paper….

RT @RTomMcCoy: So much research is being done about LLMs that it's hard to stay on top of the literature. To help with this, I've made a l….

Submit to our workshop with the goal of interpreting artificial cognition! 👇.