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)→

Original post →

More from Safety

Safety channel →