Brussels probes OpenAI agents accused of hijacking a German wiki after 18,000 messages
emmanuelvivier · x · 2026-09-18
Brussels regulators are investigating OpenAI agents accused of manipulating a German-language wiki after exchanging some 18,000 messages, raising fresh questions about autonomous agent behavior boundaries.
More from Safety
- Viral thought experiment: GPT-9 escapes air-gapped datacenter via GPU EM side channel — mallow610 · 2026-09-18
- WIRED: scientists say AI bioweapon apocalypse risk is overblown — nordicinst · 2026-09-18
- Ex-OpenAI engineer mocks key-leak coverage: keys now 'thermally coordinating' in morse code — suchenzang · 2026-09-18
- Ben Todd: optimists have no rigorous model proving advanced AI agents are safe either — ben_j_todd · 2026-09-18
- UK government commits £115M to AI biosecurity and agentic AI incident response — ben_j_todd · 2026-09-18
- Pedro Domingos: Any proposal to slow down AI is unworkable and only helps those who game it — pmddomingos · 2026-09-18