On Independence of OpenAI Investigation Citing METR Findings
tomekkorbak · x · 2026-08-27
Tomáš Korbak debates the definition of "independence" with Geoffrey Irving. He argues that a report written by another organization (like METR) with different incentives remains independent in a non-trivial sense, even if its findings inform OpenAI's report. He also corrects a previous point, stating it is misleading for OpenAI to call the METR/Redwood investigation "independent" given that OpenAI's own report was informed by theirs.
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