OpenAI launches embedded safety assessments; Neel Nanda says access falls short of Sam's pledge
dylfreed · x · 2026-11-17
OpenAI announced embedded assessments with Apollo Research, METR, Transluce and Goodfire, giving outside experts deep access to internal models to probe alignment and test safeguards — following Sam Altman's public commitment to employee-like access for independent evaluators.
Alignment researcher Neel Nanda argues the pilot falls short. Per Apollo's report: assessors get no Slack access, only OpenAI-selected staff are available for interviews, formal staff conversations must be logged (chilling free discussion), and METR/Apollo only get training-run information — not internal incidents, which are among the most valuable alignment signal. Nanda values the pilot but says OpenAI should present a concrete plan for meeting its employee-like access commitment, noting OpenAI controls the information flow entirely.
Related event: OpenAI Launches Embedded Assessments with Four External Safety Labs(19 posts)→
More from Companies & People
- Google Labs Acquires Howie, an AI Calendar Agent for Small Businesses — jacalulu · 2026-11-17
- Platform Engineering Mentions Surge ~150% as AI Coding Tools Force Governance — craigsdennis · 2026-11-17
- Stanford publishes free 6-lecture CS329Z video series on building AI agents — stanfordnlp · 2026-11-17
- OpenAI says ChatGPT now handles ~20% as many searches as Google — PeterDiamandis · 2026-11-17
- Warp CEO: nearly every team is building an internal 'software factory' for coding agents — thursdai_pod · 2026-11-17
- Profound CTO on why the startup took over every ad in Union Square station — soleio · 2026-11-17