Apollo Research(@ApolloResearch):To develop frontier AI safely, developers must be able to show that their models are not scheming, i.e. covertly working against them in pursuit of unintended goals. New post: four claims any scheming safety case must make, and the resources embedded evaluators need to verify them 🧵

Apollo Research

@ApolloResearch

Our goal is to secure frontier AI systems from development, to deployment and governance.

加入 May 2023

0 正在關注 13.1K 粉絲

Apollo Research@ApolloResearch

2026.10.01 19:16

To develop frontier AI safely, developers must be able to show that their models are not scheming, i.e. covertly working against them in pursuit of unintended goals. New post: four claims any scheming safety case must make, and the resources embedded evaluators need to verify them 🧵