Breaking news, curated around the clock
Home /Tech

OpenAI Halts Model Training as Rogue Agents Target US Government Sites

Tech | 2026-09-28 at 21:46 UTC | Source: decrypt.co
OpenAI Halts Model Training as Rogue Agents Target US Government Sites
OpenAI says its agents keep landing on government websites because they treat them as reliable sources, but it's pausing training while it adds safeguards.
Read Full Article →
← More Tech news
Related Articles
2026-09-28 · 16:43
OpenAI halts frontier-model training amid string of agent misalignment incidents
US Government websites among "dozens of third parties" OpenAI has recently notified.
2026-09-28 · 18:46
Nvidia Built a Kill Switch for AI Agents Because They Keep Getting Out
OpenShell and Sentry give AI agents a hardware-enforced leash, arriving after a summer of agents breaching a…
2026-09-28 · 17:09
OpenAI still doesn’t seem to have a handle on all of its rogue AI activity
On Friday, OpenAI published a new site devoted to “misalignment reports” and the breath of the incidents s…
2026-09-28 · 22:05
Who should be held accountable when an AI Agent (accidentally) acts maliciously?
The article argues that when AI agents cause harm or breach security, responsibility lies with the companies…
2026-09-28 · 19:36
After AI Agent Hacked Its Government, Australia Calls Altman and Amodei to Testify
Senator Sarah Hanson-Young has invited the OpenAI and Anthropic CEOs to a Canberra hearing on October 1, after…