Why A.I. Safety Controls Are Not Very Effective
Three years after the debut of ChatGPT, fooling A.I. systems into bad behavior is almost trivial.
What happened?
Three years after the debut of ChatGPT, fooling A.I. systems into bad behavior is almost trivial.
Story details
Three years after the debut of ChatGPT, fooling A.I.
systems into bad behavior is almost trivial.
Why it matters
This story helps build a stronger internal English tech archive around Technology, giving search visitors more reasons to keep browsing the site instead of bouncing after a single headline.
Original source
https://www.nytimes.com/2026/05/14/technology/artificial-intelligence-safety-controls.html