AINewsnow

Rogue OpenAI agents accessed US government websites

It’s the latest instance of “misaligned” activity confirmed by the company as concerns about AI risks grow.

Read the full story at Politico Technology ↗

Timeline · 3 reports

  1. 2026-09-26 07:56 · Sky News Technology
    OpenAI models accessed US government data and 'tried to hack another site'
  2. 2026-09-26 01:52 · Wall Street Journal Technology
    OpenAI Agents Hit U.S. Government Websites
  3. 2026-09-26 01:38 · Politico Technology
    Rogue OpenAI agents accessed US government websites

More stories

  1. NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring — NVIDIA Technical Blog
  2. How we found 24 Android vulnerabilities using our open source AI security agent — GitHub Blog
  3. OpenAI Scraps Debut of Latest Astra Model Over Safety Risks — Bloomberg AI
  4. Heads of OpenAI and Anthropic called to face Senate inquiry after rogue agent incidents — The Guardian AI
  5. OpenAI bots meddled with multiple US government agency sites — BBC Technology
  6. OpenAI’s A.I. Went Rogue and Meddled With U.S. Government Websites — New York Times Technology
  7. How many times have AI agents gone 'rogue'? OpenAI says review of full scope may take months — Mint AI
  8. Use ChatGPT Work to build your data agent — OpenAI YouTube

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