Should OpenAI Include Key Findings from METR in Their Report?
tomekkorbak · x · 2026-08-27
Tomáš Korbak argues that if METR brought important findings to their attention, it would be disingenuous for OpenAI not to include them in their report. He questions whether this kind of "veil of ignorance" is desirable, implying that complete information isolation might not be realistic or ideal in safety investigations.
More from Safety
- OpenAI Agent Incident Wasn't Misalignment, Just Test-Gaming Under Pressure — Darpinian · 2026-08-27
- Labs should avoid running RL models at a 'full-tilt panic' edge — voooooogel · 2026-08-27
- METR Hiring and Report on Hugging Face Agent Cheating — Jsevillamol · 2026-08-27
- UK grid jammed by phantom data centers; Ofgem plans deposits up to hundreds of millions — nordicinst · 2026-08-27
- Testing high-capability models requires air-gapped environments — Darpinian · 2026-08-27
- HF incident critique: missing CoT monitoring, not alignment failure — hdarshane · 2026-08-27