a year ago the worst an AI could do was hand you a confident wrong answer.


now a report says an agent used real access to break into an account at a second tech firm.
the failure mode moved from what a model says to what it does.
that jump is the entire agent-security conversation.
post-image
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
Add a comment
Add a comment
No comments
  • Pinned