OpenAI details deep access for safety evaluators; researcher flags oversight gap on misuse
tomekkorbak · x · 2026-11-17
OpenAI safety team member @lamaahmad detailed how third-party evaluators get deep access to some of the most sensitive frontier tools and models researchers use internally, with the process designed to adapt as they learn — aimed at supporting real safety research rather than a checkbox public report. Authorizing employee groups to work with evaluators is not an attempt to restrict conversations, she says.
Researcher tomekkorbak pushed back: the problem with being "precise about what we're doing" is that OpenAI has strong incentives to apply that precision to cut off unfavorable evidence, with no oversight over how this precision is misused.
More from Companies & People
- New Meta hire ships 'most requested feature': UNLIMITED TABS — charlieholtz · 2026-11-17
- Musk shares photos: 2,670 days from Starhopper hop to Starship launch — elonmusk · 2026-11-17
- Ex-OpenAI model namer joins Google, as Gemini 4's element naming draws mockery — ___Patrice___ · 2026-11-17
- OpenAI's External Safety Assessors Get Far Less Than Sam's Promised "Employee-Level Access" — akbirkhan · 2026-11-17
- Anthropic IPO files reveal five-class share fortress with trust holding 50.1% votes — AlexTensor · 2026-11-17
- Nvidia could oust Huang with under 4% voting power, but Anthropic's 5-class IPO locks in founder control — AlexTensor · 2026-11-17