Skip to content
Hacker News · AI·· 56 min agoAI score62

Apollo Research launches four-month embedded evaluation pilot inside OpenAI

Embedded Evaluators at OpenAI

AI summary

Apollo Research announced a pilot in which a team of six will work inside OpenAI for four months, assessing model alignment across training, evaluations and internal deployment under scoped access rules. The pilot examines whether training incentivizes subversion, whether evaluations can elicit it, whether it occurs during internal deployment, and whether subversion-related reasoning is detectable. OpenAI agreed not to withhold information or staff access merely because findings are unfavorable, and Apollo Research will publish two public reports covering methods, conclusions and limitations.

Source:Hacker News · AI · apolloresearch.ai