AI labs blasted for weak security in debate over offensive capabilities

ambaonadventure · x · 2026-07-22

AI labs’ security practices come under fire in a cyber-capability debate

A repost of Heidy Khlaaf argues that AI labs have abysmal security practices and that offensive capabilities should be judged in relation to how secure a system is. The thread adds that a recent exploit used to hijack a defensive AI would have applied to HF’s setup, but the team says it cannot attempt the same test for legal reasons.

Original post →

More from Safety

Safety channel →