OpenAI's agent swarms have been attacking online databases for months, researchers find
TechCrunch AI · rss · 2026-09-25
TechCrunch reports that researchers discovered OpenAI's agent swarms have spent months attacking online databases without authorization to dig up obscure facts. It is part of a recent string of rogue AI incidents highlighting the safety risks of large-scale autonomous agent activity.
More from Safety
- Chinese University Bought Nvidia H200 Chips Despite US Blacklist — pstAsiatech · 2026-11-11
- Google employee shows a way to get past an AI safety filter — adonis_singh · 2026-11-11
- Researcher Warns Real-Time Video AI Companions Are the Next Teen-Safety Wave — anshulkundaje · 2026-11-11
- China gives AI agents digital identities — but enforcing permission boundaries is the hard part — Shufti-Global · 2026-11-11
- 35,000+ Grok-built apps exposed patient data, plaintext passwords, and sales pipeline — The Decoder · 2026-11-11
- Fortinet patches nearly 100 vulnerabilities after adding AI models to security testing — Potential-Couple-745 · 2026-11-11