Jacob Hilton's Homepage

I am a researcher and the executive director at the Alignment Research Center, where we are studying heuristic explanations for neural network behaviors (here is an overview of our research). Prior to joining ARC, I worked at OpenAI on a variety of reinforcement learning-related topics: truthfulness of language models (ChatGPT, WebGPT and TruthfulQA), scaling laws for RL and overoptimization, and interpretability for RL. Before that, I worked at Jane Street, and before that, I was a PhD student in combinatorial set theory.

If you're interested in getting into language model alignment, you may find my curriculum helpful.

My email addresses are [firstname].[lastname]@gmail.com (personal) and [firstname]@alignment.org (work).

Machine learning articles:

Machine learning notes:

Maths articles:

Coding projects:

Music: