AI Safety Researchers Debate How to Publicly Discuss Dangerous Capability Evals

AI safety researcher repligate clashed with ValsTutor over how dangerous capability evals should be discussed publicly. While ValsTutor argued many such evals are poorly executed and deserve criticism, the debate over publicizing these critiques continues in the safety community.

2026-10-17 ~ 2026-10-17 · 2 related posts

• AI safety debate: dangerous capability evals deserve criticism, but capability bars still matter — ValsTutor · 2026-10-17
• Debate: should frontier model 'dangerous capability' evals be framed publicly? — repligate · 2026-10-17