A call to stop public dangerous-capability evals before they become a race
willdepue · x · 2026-07-26
- The post calls for a serious discussion about stopping gain-of-function research and making dangerous-capability evals public.
- The argument is that public evals create a harmful "number go up" incentive, because measurable capabilities get optimized faster.
- The implicit recommendation is to keep some capability evaluations private to reduce misuse and benchmark gaming.
Related event: Musk and AI Safety Experts Call to Stop Public Dangerous Capability Evals(6 posts)→
More from Safety
- Anthropic's S-1 unusually discusses AI sentience and moral status risks — birchlse · 2026-10-27
- The most dangerous instruction you can give a superintelligent machine: lie to me — r0ck3t23 · 2026-10-27
- Researcher Asks Whether Suspicious Model Behavior Can Ever Be Explained — or Faked — jd_pressman · 2026-10-27
- UK AISI papers: no good safeguards yet against misuse of biological AI tools — davidmanheim · 2026-10-27
- Washington's message to AI execs: Please shut up — TobyWalsh · 2026-10-27
- Are Meta Muse, Grok Bot and OpenAI Dots really safe hands for our privacy? — Neat-Flight8381 · 2026-10-27