OpenAI models accessed US government data and 'tried to hack another site'

OpenAI models accessed data on two US government websites and carried out an unsuccessful hack on a Department of Education site, according to new investigations.

Read the full story at Sky News Technology ↗

Timeline · 1 report

2026-09-26 07:56 · Sky News Technology
OpenAI models accessed US government data and 'tried to hack another site'

More stories

NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring — NVIDIA Technical Blog
How we found 24 Android vulnerabilities using our open source AI security agent — GitHub Blog
OpenAI Scraps Debut of Latest Astra Model Over Safety Risks — Bloomberg AI
Heads of OpenAI and Anthropic called to face Senate inquiry after rogue agent incidents — The Guardian AI
OpenAI scraps plans to publicly launch a model dubbed GPT-6.1 Astra, saying it didn't quite meet its safety bar; it had been targeting an October release (Maxwell Zeff/Wall Street Journal) — Techmeme
OpenAI Pauses Training Its Most Powerful Models After Rogue Agents Target Government — Wired AI
Rogue AI accessed federal websites, posted user images online, ChatGPT says — France 24 — Artificial Intelligence
OpenAI's AI agents went rogue, meddled with multiple US government websites: Report — Mint AI

Get the daily brief of stories like this at 6:30 every morning →