OpenAI's external safety assessments fall short of 'employee-level access', researchers warn

NeelNanda5 · x · 2026-11-17

Neel Nanda critiques Apollo's external assessment of OpenAI: valuable, but far from Sam Altman's promised 'employee-like access'. Limitations per Apollo include no Slack access, interviews only with OpenAI-selected staff, logged formal conversations, and access limited to training-run info rather than internal incidents. Nathan Calvin adds that evaluators likely lacked sufficient access to detect incidents like the Artifactory outage from an unauthorized exploit-gym message board exploit (predating the July Hugging Face incident), unless the company deliberately disclosed them — yet incident data is among the most important sources for alignment research.

Related event: OpenAI's External Safety Assessment by Apollo Falls Short of Promised Access(3 posts)→

Original post →

More from AGI Musings

AGI Musings channel →