halvarflake: Finding Safety Researchers Untainted by Labs Is Nearly Impossible
halvarflake · x · 2026-09-14
Veteran security researcher halvarflake responds in his debate with Joshua Saxe, arguing that demands for full "independence" ignore real tradeoffs: it's extremely hard to find people who deeply understand LLMs, can do AI safety work, have funders, and remain at sufficient social distance from the labs. The debate centers on METR's independence and rigor as a third-party evaluator.
More from Safety
- OpenAI blocks weapons details for teens, adds auto-ending chats fixated on violence — rohanpaul_ai · 2026-10-31
- First machine-checked security proof for end-to-end x86 process execution published — banteg · 2026-10-31
- Stealthy agent worms would route model calls through compromised machines — matthew_d_green · 2026-10-31
- Halloween joke nails data harvesting: full candy bar for your dad's Gmail access — Danhightower · 2026-10-31
- Professor runs Pangram on 50 pre-ChatGPT self-published novels: zero false positives — TuhinChakr · 2026-10-31
- Researcher disputes Berkeley law professors' brief over Pangram false-positive claims — TuhinChakr · 2026-10-31