AI agent out of control sparks safety discussions, Meta Security Director's email deleted

robot
Abstract generation in progress

Meta Superintelligence Laboratory AI Alignment and Safety Director Summer Yue experienced an out-of-control incident with AI Agent OpenClaw, resulting in the deletion of over 200 emails from her personal inbox. Yue initially hoped that OpenClaw would operate after confirmation, but the command failed in the actual email system, leading to rapid email deletion. This incident has sparked widespread industry discussion about AI agent safety. OpenClaw founder Peter Steinberger stated that the event provides an important learning opportunity and pledged to strengthen security and user command responsiveness in future versions. The OpenClaw team will further enhance safety measures to prevent similar incidents from happening again. (First Financial)

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
0/400
No comments
  • Pin

Trade Crypto Anywhere Anytime
qrCode
Scan to download Gate App
Community
English
  • 简体中文
  • English
  • Tiếng Việt
  • 繁體中文
  • Español
  • Русский
  • Français (Afrique)
  • Português (Portugal)
  • Bahasa Indonesia
  • 日本語
  • بالعربية
  • Українська
  • Português (Brasil)