This sounds like a great idea, maybe even allow a K-budget

Cursor is down....

🚨 New paper drop! 🚨 🤔 When a transformer sees a sequence that could be explained by many rules, which rule does it pick? It chooses the simplest sufficient one! 🧵👇

Waiting for indexing of github... :)

🚨New paper! We know models learn distinct in-context learning strategies, but *why*? Why generalize instead of memorize to lower loss? And why is generalization transient? Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵 1/

Amazing! I was wondering why there is no good curated dataset on humans playing game of 24. Here it is now :)

Very cool experiment

Dear NeurIPS Conference -- it seems OpenReview is down entirely, and we cannot submit reviews for the upcoming review deadline tonight. Please share if you are having a similar issue. #neurips2025

🧵 What if two images have the same local parts but represent different global shapes purely through part arrangement? Humans can spot the difference instantly! The question is can vision models do the same? 1/15

New position paper! Machine Learning Conferences Should Establish a “Refutations and Critiques” Track Joint w/ Sanmi Koyejo Joshua Kazdan Yegor Denisov-Blanch Francesco Orabona Koustuv Sinha Jessica Zosa Forde Jesse Dodge Susan Zhang Brando Miranda Matthias Gerstgrasser isha Elyas Obbad 1/6

100%

The real developer moat isn't coding anymore. LLMs can pump out functions faster than most of us can type. The moat is in the spaces between the code. It's knowing why your database is slow when the logs show nothing obvious. It's understanding that the "simple" feature request

- 8000 USD / Mtok - Input: 10 tok/s - Output: 2 tok/s - Latency: 10 mins ~ 2 weeks - 12h downtime per day Integrating this agent into a multi agent system is challenging......

What drives in-context learning in LLMs? New paper: Provable Low-Frequency Bias of In-Context Learning of Representations. We show LLMs have a low-frequency bias when learning representations in context, offering a theoretical answer to several previously open questions. 🧵👇

Super excited to be joining Goodfire! I'll be scaling up the line of work our group started at Harvard: making predictive accounts of model representations by assuming a model behaves optimally (i.e., good old rational analysis from cogsci!)

Pontificating about a system's 'intentions' doesn't shed any light on the technical problem of eliciting its capabilities. It just confuses people in a characteristically AI-safety-community way.

Introducing the Environments Hub RL environments are the key bottleneck to the next wave of AI progress, but big labs are locking them down We built a community platform for crowdsourcing open environments, so anyone can contribute to open-source AGI