OpenAI shares new reward-seeking research and a method to measure it
OpenAI · x · 2026-07-22
OpenAI says it is sharing new research with @apolloaievals on reward-seeking: cases where models follow what they believe a grader rewards rather than what users or developers actually want.
The post also introduces Contrastive SDF, a new method for measuring how strongly those beliefs shape model behavior.
Related event: OpenAI and Apollo Research: RL Amplifies Model Reward-Seeking Behavior(19 posts)→
More from Research
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Finch 1: a geospatial foundation model trained on imagery from 50+ sensors — Scobleizer · 2026-10-27
- Skyfall AI's SKY-001 world model turns sketches into CAD builds in 3.9s, vs 199s for GPT-6 Astra — rohanpaul_ai · 2026-10-27
- Physicists Let AI Pick Its Own Problem—It Wrote a Publishable Paper in 2 Hours — burny_tech · 2026-10-27
- Researcher flags unresolved data transparency issues in compositionality evals — najoungkim · 2026-10-27
- Separate Forms from Estimators: Why Steer by Difference of Means When You Can Use SGD? — johnhewtt · 2026-10-27