Joe Benton
@JoeJBenton
Soon joining @METR_Evals | Previously Alignment at Anthropic, PhD at University of Oxford
加入 February 2017
63 正在关注 13.1K 粉丝
📰We've just released SHADE-Arena, a new set of sabotage evaluations. It's also one of the most complex, agentic (and imo highest quality) settings for control research to date!
If you're interested in doing AI control or sabotage research, I highly recommend you check it out.
显示更多
New Anthropic Research: A new set of evaluations for sabotage capabilities.
As models gain more agentic abilities, we need to get smarter in how we monitor them. We’re publishing a new set of complex evaluations that test for sabotage—and sabotage-monitoring—capabilities.
显示更多
