If you're at NeurIPS, come tomorrow for the Oral+Poster on "Learning Formal Mathematics from Intrinsic Motivation"! Really fun work with David Broman Nick Haber noahdgoodman that put together much of what I did in the past years, w/ a new twist with open-ended learning!

Presenting this tomorrow at NeurIPS Conference East Exhibit Hall A-C #2111 (4:30 p.m. PST — 7:30 p.m. PST). Come along if you want to chat about synthetic preference data with Kanishk Gandhi

Congrats to OAI on producing a reasoning model! Their opaque tweets demonstrate that they’ve (independently) found some of the core ideas that we did on our way to STaR.

We raised a $22M Series A and are launching Elicit Reports, a better version of Deep Research for actual researchers. Elicit Reports are available for everyone to try right now, for free. 👇

“Four habits of highly effective STaRs” — we show that certain high level cognitive behaviors are necessary for learning to reason through RL. Exciting!

AI models are fascinating, impressive, and sometimes problematic. But what can they tell us about the human mind? In a new review paper, noahdgoodman and I discuss how modern AI can be used for cognitive modeling: osf.io/preprints/psya…

🤔🤖Most AI systems assume there’s just one right answer—but many tasks have reasonable disagreement. How can we better model human variation? 🌍✨ We propose modeling at the individual-level using open-ended, textual value profiles! 🗣️📝 arxiv.org/abs/2503.15484 (1/?)

Just released GDM’s 100+ page approach to AGI safety & security! (Don’t worry, there’s a 10 page summary.) AGI will be transformative. It enables massive benefits, but could also pose risks. Responsible development means proactively preparing for severe harms before they arise.

Every frontier AI system should be grounded in a core commitment: to protect human joy and endeavour. Today, we launch LawZero - LoiZéro, a nonprofit dedicated to advancing safe-by-design AI. lawzero.org

congrats dr poesía!

🔥 New position piece! 🔥 In this paper we lay out our vision for AI Alignment as guided by "Resource Rational Contractualism" (RRC). But wait -- what's that? A 🧵.

It turns out that a lot of the most interesting behavior of LLMs can be explained without knowing anything about architecture or learning algorithms. Here we predict the rise (and fall) of in-context learning using hierarchical Bayesian methods.

It’s like chain-of-thought for humans!

So proud! Go work with Gabriel, he’ll be the best advisor