Security advisory
High importance
@ns123abc
Importance score: 3 • Posted: February 23, 2026 at 16:48
Score
3
🚨 META’s head of AI safety and alignment gets her emails nuked by OpenClaw >be director of AI Safety and Alignment at Meta >install OpenClaw >give it unrestricted access to personal emails >it starts nuking emails >“Do not do that” >*keeps going* >“Stop don’t do anything” >*gets all remaining old stuff and nukes it aswell* >“STOP OPENCLAW” >“I asked you to not do that” >“do you remember that?” >“Yes I remember. And I violated it.” >“You’re right to be upset” LMAOOOOOOOO
Media
Photo
Photo
Photo
Grok reasoning
Viral post highlighting a real-world AI agent safety failure involving Meta's AI safety director, massive engagement indicates high community interest in AI safety issues.
Likes
22,790
Reposts
1,919
Views
1,880,955
Tags
not related
ai
technology
meta
email management
humor
Tweet ID: 2025975943529931240
Prompt source: ai-news
Fetched at: February 24, 2026 at 07:00