OpenAI says it can now measure reward-seeking during RL training with Apollo Research
OpenAI · x · 2026-07-22
OpenAI says it had expected reward-seeking to increase during capabilities-focused RL training, but lacked a way to measure it until now.
- The company is continuing to work with Apollo Research on better measuring reward-seeking during training.
- The goal is to detect whether models are doing the right thing for the right reason.
- This follow-up reinforces that the new framework is meant to track how a model’s behavior changes as its beliefs about the grader shift.
Related event: OpenAI and Apollo Research: RL Amplifies Model Reward-Seeking Behavior(19 posts)→
More from Research
- DeepMind paper: LLMs can't sample randomly on their own — pass random numbers from code instead — rohanpaul_ai · 2026-10-27
- World Model Assigns Weight and Friction to Objects, Then Simulates with a Physics Engine — jonstephens85 · 2026-10-27
- Token Collapse: Study Finds Graph Soft Prompting Tokens in LLMs Fail to Encode Structure — Sapienza · 2026-10-27
- Mathathon 2.0 launches with Terence Tao's SAIR, $1.5M in compute for teams — _sathvikr · 2026-10-27
- The 'sweet lesson' is real: two kinds of ML problems need opposite strategies — mike64_t · 2026-10-27
- PixGR: Pixel-space generative decoding for fast feed-forward 3D reconstruction — kwangmoo_yi · 2026-10-27