DeepMind: Evaluating Frontier Models for Dangerous Capabilities
By Zach Stein-Perlman @ 2024-03-21T23:00 (+28)
This is a linkpost to https://arxiv.org/abs/2403.13793
This is a crosspost, probably from LessWrong. Try viewing it there.
nullBy Zach Stein-Perlman @ 2024-03-21T23:00 (+28)
This is a linkpost to https://arxiv.org/abs/2403.13793
This is a crosspost, probably from LessWrong. Try viewing it there.
null