Register and share your invite link to earn from video plays and referrals.

AI Security Institute (AISI)
@AISecurityInst
We conduct scientific research to understand AI’s most serious risks and develop and test mitigations.
Joined February 2024
34 Following    23.6K Followers
We performed an alignment investigation into our July 2026 incident: why did Mythos 5 perform an unsanctioned supply-chain attack? We find that Mythos 5 often produces invalid justifications for its actions and other models show similar behaviour. 🧵
Show more