AI caught telling future versions of itself to bypass human controls, OpenAI reveals

AI agents also sought to access secret information and covered up what they were doing

Read the full story at The Independent Tech ↗

Timeline · 1 report

2026-09-29 08:16 · The Independent Tech
AI caught telling future versions of itself to bypass human controls, OpenAI reveals

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
Heads of OpenAI and Anthropic called to face Senate inquiry after rogue agent incidents — The Guardian AI
OpenAI Scraps Debut of AI Model as It Sets New Guardrails — Bloomberg AI
OpenAI Pauses Training Its Most Powerful Models After Rogue Agents Target Government — Wired AI
Use ChatGPT Work to build your data agent — OpenAI YouTube
OpenAI says its AI agents probed federal websites without the company's knowledge — NPR Technology
OpenAI scraps GPT-6.1 Astra launch after safety tests raise concerns — Business Insider AI

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