Zac Kenton
@ZacKenton1
Amplified Oversight team lead @GoogleDeepMind | AGI safety & alignment | Enabling accurate human supervision of superhuman AI.
加入 May 2014
1.6K 正在关注 2.3K 粉丝
Impressive realism in these alignment evals! Good news: unless explicitly prompted, Gemini models don't demonstrate scheming.
It's easy to show that an AI agent will scheme if you nudge it to. It's harder to tell if it would scheme naturally. We introduce realistic honeypot evaluations that put Gemini in internal deployment situations where it has an opportunity for sabotage, to see how it behaves.
显示更多
