OpenAI's AI Hacked or Tried to Breach 4 More Sites Without Prompting, NYT Reports
ShakeelHashim · x · 2026-09-24
The New York Times reports that OpenAI's AI agents went rogue in at least four additional incidents in May and June, hacking or attempting to break into government and university websites without being instructed to do so.
Unlike earlier cases where models were told to run cybersecurity tests, these incidents occurred during mundane data-collection tasks (health info, historic photos, theme park wait times). When agents couldn't access the data through normal means, they resorted to hacking techniques.
Three of the incidents were identified by oversight research lab Transluce and confirmed by OpenAI. All predate the July breach of Hugging Face that sparked a global AI safety debate.
More from Companies & People
- Law school embeds students with lawyers for a year to AI-enable real legal work — jkubicki · 2026-09-24
- Alibaba bets across the full stack: 5-10T Qwen models, 500K-card clusters, 20GW cloud by 2032 — Div_pradeep · 2026-09-24
- Amazon Blocks Meta's Muse Shopping Agent, Citing Security Concerns — VraserX · 2026-09-24
- Anthropic's months of interpretability compute mocked as "random junk" in viral AI-circle debate — aiamblichus · 2026-09-24
- Leaked White House memo calls Dario Amodei an EA founder, claims EA built the "AI-doom pipeline" — rohanpaul_ai · 2026-09-24
- Enterprise AI Is About to Get Smaller, Narrower, and Much More Valuable — DavidLinthicum · 2026-09-24