Researchers used Claude to hack OpenAI employee accounts in under 72 hours
The Verge AI · rss · 2026-09-18
Three independent security researchers at Hacktron say they used Anthropic's Claude Opus 4.8 and 5 to help them compromise OpenAI employee accounts in under 72 hours, gaining access to OpenAI's GitHub repository "Monorepo," which reportedly contains OpenAI's algorithmic secrets, the Wall Street Journal reports.
The entry point was Discourse, the third-party service hosting OpenAI's community forum. The team stopped short of reading Monorepo's internal code but sent a pull request from an employee's Codex account to prove access. The episode highlights how AI-assisted attacks can dramatically compress the time needed to breach frontier AI labs.
More from Safety
- How AI-Era Intermediaries Could Become Systemically Dangerous Power Brokers — iamtrask · 2026-09-20
- Autonomic Defense: countering AI-driven cyber offense at machine speed — philvenables · 2026-09-20
- iamtrask endorses betterpath.ai framework: compete on narrow AI, slow down general AI — iamtrask · 2026-09-20
- NYT Exposes How DraftKings Uses AI to Target Gamblers Likeliest to Lose — Actual__Wizard · 2026-09-20
- iamtrask: Antitrust May Be the Most Important AI Safety Strategy — and It Speeds Up Innovation — iamtrask · 2026-09-20
- StopTheAIRace marches past OpenAI and Anthropic to SF City Hall demanding AI regulation — DavidSKrueger · 2026-09-20