Apollo Research(@ApolloResearch):Black-box access may soon no longer be enough to robustly make or verify safety and security claims. Deeper, white-box access is a necessary update to counter 'evaluation awareness' and keep loss-of-control evaluations state of the art. A new policy blog explains why. 🧵

Apollo Research

@ApolloResearch

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

Joined May 2023

0 Following 11.7K Followers

Apollo Research@ApolloResearch

2026.05.27 17:15

Black-box access may soon no longer be enough to robustly make or verify safety and security claims. Deeper, white-box access is a necessary update to counter 'evaluation awareness' and keep loss-of-control evaluations state of the art. A new policy blog explains why. 🧵