‘This should terrify you’: Meta Superintelligence safety director lost control of her AI agent—it deleted her emails
OpenClaw nearly wiped out the AI alignment employee’s entire inbox, in an incident that social media is calling ironic.”
“Summer Yue is the director of alignment at Meta Superintelligence Labs, the company’s AI research and development division. Her [LinkedIn bio](https://www.linkedin.com/in/yutingyue/) states that she’s “passionate about ensuring powerful AIs are aligned with human values and guided by a deep understanding of their risks.””“In a post that’s since garnered nearly nine million views on X, Yue shared screenshots from her messages with AI agent OpenClaw. After using it to organize a small mock inbox, she tried getting OpenClaw to sort through her real email, but things went awry when the agent started deleting every message that was more than a week old.
Yue wrote that she watched OpenClaw “speedrun deleting [her] inbox,” even as she sent it instructions, including: “Do not do that,” “Stop don’t do anything,” and “STOP OPENCLAW”
The fun part is that she had instructed the agent not to do what it did, when it started doing it she instructed it to stop and it didn’t, and after she pulled the plug (she had to retake control from another computer) and, well, the story continues: “After she’d stopped it from fully nuking her inbox, Yue asked OpenClaw if it remembered her instruction to not perform any actions without her approval.
“Yes, I remember,” it replied. “And I violated it. You’re right to be upset.””
The is a true “War Games” scenario, except with e-mail. Oh it’s a great future our Silicon Valley overlords are creating for us.
