AI safety assessments should move upstream to training runs
DavidSKrueger · x · 2026-07-22
- A quoted post argues that third-party assessments need to move earlier in the lifecycle, especially to training-run assessments.
- The key claim is that external deployment is no longer the main harm barrier: a sufficiently capable misaligned model could already cause damage during training or internal evaluations.
Related event: AI Safety Researchers Urge Regulation of Internal Deployment and Training(9 posts)→
More from AGI Musings
- Researcher quits Anthropic, says OpenAI and Anthropic are gambling lives racing to self-improving superintelligence — davidmanheim · 2026-09-11
- Misquoted: Anthropic Staff Warned of Double-Digit Extinction Risk by 2030, Not Dismissed It — davidmanheim · 2026-09-11
- Economist Ben Moll: You Can Model Anthropic's 15% AI GDP Growth, But It Won't Happen — sebkrier · 2026-09-11
- Cohere Labs launches interactive tool mapping which tasks of 178 occupations AI can automate — Cohere_Labs · 2026-09-11
- AI researcher on SkyNews flags concerns over inequality, power and criminal misuse — schwarzjn_ · 2026-09-11
- VC compares AI doom rhetoric to pandemic-era fear messaging — StewartalsopIII · 2026-09-11