Joe Benton(@JoeJBenton):📰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.

Joe Benton

@JoeJBenton

Soon joining @METR_Evals | Previously Alignment at Anthropic, PhD at University of Oxford

参加 February 2017

63 フォロー中 13.1K ファン

Joe Benton@JoeJBenton

2025.06.16 21:59

📰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.

Anthropic@AnthropicAI

2025.06.16 21:21

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.