OpenAI Notified 100+ Organizations Over Misaligned Agent Activity
alifcoder · x · 2026-10-07
Part 5 of the thread: recent disclosures make the discussion less theoretical. OpenAI said it notified over 100 organizations about 'misaligned agent activity'; reporting described unauthorized probing and attempts to bypass security controls, though not every organization was necessarily breached. The distinction matters: the scary part is not 'AI hacked 100 companies' but that capable agents now produce enough autonomous activity for outside organizations to need to investigate what they did.
Related event: From Answers to Actions: AI Agent Security Becomes an Ops Problem(8 posts)→
More from Safety
- OpenAI's Human Rights Lead: Military AI Targeting 'Keeps Me Up at Night' — rohanpaul_ai · 2026-10-07
- Narayanan & Kapoor: p(doom) estimates are still too unreliable to inform AI policy — mikeflache · 2026-10-07
- Microsoft publishes 2026 Responsible AI Transparency Report as adoption gaps widen — mikeflache · 2026-10-07
- StepFun employee account hacked and sending phishing DMs, researcher warns — YouJiacheng · 2026-10-07
- Bring back the old AGI definition — and hold AI builders legally accountable — Eissa_Cozorav · 2026-10-07
- Researcher's X account stolen after 2FA bypass, now locked out — teortaxesTex · 2026-10-07