Ex-OpenAI researcher: external safety assessments fall short of Altman's pledge
tomekkorbak · x · 2026-11-17
- Departing OpenAI researcher balesni says that in his final week, external auditors were still haggling over small access improvements to safety-relevant information, despite Sam Altman's public commitment to "employee-like access" — and nobody could explain why.
- OpenAI simultaneously announced embedded assessments with METR, Apollo Research, Transluce, and Goodfire, but critics note assessors get no Slack access (where all OpenAI safety debate happens) and OpenAI itself picks which employees they may talk to.
- Reposter tomekkorbak concludes employees seemingly couldn't hold leadership to Altman's public commitments.
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