Research

Our research paper on using reinforcement learning to optimize SAT microlearning. Click to read the full paper.

We are replacing the existing GPT-4o-based model for Operator with a version based on OpenAI o3. The API version will remain based on 4o.

Introducing Codex: a cloud-based software engineering agent that can work on many tasks in parallel, powered by codex-1. With Codex, developers can simultaneously deploy multiple agents ...

Codex is a cloud-based coding agent. Codex is powered by codex-1, a version of OpenAI o3 optimized for software engineering. codex-1 was trained using reinforcement learning on real-wor...

We study how training on incorrect responses can cause broader misalignment in language models and identify an internal feature driving this behavior—one that can be reversed with...