Compare model features, migration guidance, and prompting best practices across OpenAI models.

ALT: Star Fox 64 Gameplay

We study high-dimensional distribution learning in an agnostic setting where an adversary is allowed to arbitrarily corrupt an $\varepsilon$-fraction of the samples. Such questions have a rich hist...

Compilers, especially method just-in-time compilers, operate on one function at a time. It is a natural code unit size, especially for a dynamic language JIT: at a given point in time, what more infor...

Our progress toward recursive self-improvement, and its implications.

I’m at Anthropic’s Code w/ Claude event in 2026, and I’ll be live blogging the keynote and a few other notes throughout the day.

The Reinforcement Learning from Human Feedback Book

Course lectures and talks on RLHF and post-training.

And yes, I hate consortia too.