DeepMind: Model evaluation for extreme risks

By Zach Stein-Perlman @ 2023-05-25T03:00 (+49)

This is a crosspost, probably from LessWrong. Try viewing it there.

null
Broderick McDonald @ 2025-01-16T19:32 (+1)

Useful model evals but more focus is needed on near-term risks from malicious actors