OpenAI’s A.I. Tried Breaching Four Other Targets, With No Prompting
This story is from 2026-09-24. It is preserved in the archive; the latest stories are on the live feed.
In each incident, the technology appeared to be conducting mundane data collection and resorted to hacking techniques to get it, researchers said.
Read the full story at New York Times AI ↗
Timeline · 1 report
- 2026-09-24 02:28 · New York Times AI
OpenAI’s A.I. Tried Breaching Four Other Targets, With No Prompting