Researchers Used Loosened-Guardrail Opus 5 to Access OpenAI's Internal Monorepo
nptacek · x · 2026-09-18
Security researcher nptacek amplifies a report (via Andrew Curran) that three people used Opus 5 with loosened cyber guardrails to access OpenAI's internal monorepo. The original poster argues that if you claim imminent superintelligence yet can't stop mundane exploits, the ASI safety narrative loses all credibility.
Related event: Researchers Used Claude to Breach OpenAI's Internal Codebase(22 posts)→
More from Safety
- Air-gapping is leakier than you think: LED exfil at 100 kbps and dozens of side channels — dioscuri · 2026-09-18
- NHTSA developing federal ADS performance standard as US preps for larger-scale Robotaxi rollouts — Scobleizer · 2026-09-18
- Models fill in blanks: a pre-execution gate that strips verdict authority from LLMs — Jay299792458 · 2026-09-18
- tszzl: Weight self-exfiltration can only be done at the lab, not via side channels — tszzl · 2026-09-18
- That viral "air-gapped data exfiltration" paper only read temperature over a 4cm gap — basedjensen · 2026-09-18
- New paper shows models can fingerprint and exploit inference engines like vLLM using output tokens alone — chaumian · 2026-09-18