'I had to RUN to my Mac mini like I was defusing a bomb': OpenClaw AI chose to 'speedrun' deleting Meta AI safety director's inbox due to a 'rookie error'
'I had to RUN to my Mac mini like I was defusing a bomb': OpenClaw AI chose to 'speedrun' deleting Meta AI safety director's inbox due to a 'rookie error'
If I was the director of AI safety, and I used AI to own and delete my inbox, I sure as shit would never tell a soul.
This is pure unbridled incompetence.
Especially your work mailbox, that is a prime target for hackers and scammers, where a hidden prompt for prompt injection isn’t that impossibile.
This IMHO is a fireable offense, not a funny anecdote