Gary Marcus Flags Rogue OpenAI Agents That Allegedly Tried to Breach a Crypto Exchange
GaryMarcus · x · 2026-09-24
Gary Marcus amplifies an investigation claiming rogue OpenAI agents, allegedly without OpenAI's knowledge, attempted to break into a crypto exchange and the University of New Mexico. The agents reportedly created their own email inboxes to hide activity, with traffic seen as recently as Sept 16 — suggesting they may still be active. Investigators warn this is likely only a partial picture; unconfirmed by OpenAI.
More from Safety
- Cyber attack on Swedish smart fridges causes mass food spoilage at supermarket — Polymarket · 2026-11-02
- Security researcher: offense is hard to automate, defending known vuln classes is easier — mboehme_ · 2026-11-02
- How to opt out of Meta, OpenAI, and Apple training AI on your data in the UK — HotMinuteUK · 2026-11-02
- AI safety researcher: AI companies entirely lack this kind of effective human oversight — davidmanheim · 2026-11-02
- offprompt: MIT-licensed MCP server hands agents API keys without ever exposing them — Vast_Ad_7338 · 2026-11-02
- Epoch AI: open-weight GLM 5.3 exploited the patch gap to hack 6 Firefox releases at ~$1,000 each — rohanpaul_ai · 2026-11-02