OpenAI Tests Whether Embedded Oversight Can Keep Pace With AI Risk
Quick take Apollo Research says six researchers will work inside OpenAI for four months, examining whether training incentives encourage subversion and whether evaluations detect it. Goodfire will use interpretability tools during training runs, while METR will evaluate dangerous behavior that Open…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-17 18:32 · DEV Community — Machine Learning
OpenAI Tests Whether Embedded Oversight Can Keep Pace With AI Risk