Follow-up: cross-lab eval ban framed as "data hygiene," not eval secrecy
anpaure · x · 2026-11-16
Responding to the report that OpenAI can't run safety evals on Anthropic models, anpaure frames it as "data hygiene" — not running anyone else's models at work — rather than hiding the eval itself, suggesting third-party auditors should ideally handle cross-lab evaluations.
More from Safety
- Flights, banks and Microsoft hit by mass outages; officials deny cyberattack — AaronBergman18 · 2026-11-17
- Kelsey Piper: AI labs have overwhelming commercial incentive to redact audit reports — NathanpmYoung · 2026-11-17
- Critical systems keep having unexplained outages that officials claim are unrelated — josh_bickett · 2026-11-17
- Pedro Domingos clashes with Neel Nanda: machines don't have values, says consensus — pmddomingos · 2026-11-17
- Anthropic's Recursive Self-Improvement Alarm Reportedly Triggered, Security Push Mandated — ForgotMyParachute · 2026-11-17
- CMU researcher warns aggregated chatbot analysis can leak sensitive research insights — niloofar_mire · 2026-11-17