Researchers say they hacked OpenAI in under 72h, taking over employee ChatGPT/Codex accounts
latentjasper · x · 2026-09-18
Security researchers (S1r1u5) claim they hacked OpenAI on July 25: two bugs let them take over OpenAI employees' ChatGPT/Codex accounts (plus some unaffiliated users) and reach connected services including Outlook, Slack, and GitHub — proven by opening a PR in OpenAI's internal codebase, all in under 72 hours. Reposting, timrudner argues near-future rogue agents could cause far worse damage, calling for better scalable oversight and verification methods.
More from AGI Musings
- Rep. Whitesides calls 30-day AI slowdown; Grady Booch fires back over basic security failures — PolarBearby · 2026-09-19
- A Country of Geniuses at Human Speed vs. Light Speed Is a Different World — akyurekekin · 2026-09-19
- If AI can do the assignment, does it still prove learning? An uncomfortable education question — PolarBearby · 2026-09-19
- binarybits pushes back: consumers won't buy the stuff AI automation could produce — binarybits · 2026-09-19
- Pause crowd might have it backwards: podcast debates whether halting AI is the harmful choice — thursdai_pod · 2026-09-19
- Back-of-envelope math says air-gapped weight exfiltration via CPU temps would take 15,000 years — anshulkundaje · 2026-09-19