Researchers use Claude and GPT-5.6 to ethically hack OpenAI employee accounts
pstAsiatech · x · 2026-09-19
Cybersecurity researchers at Hacktron AI, operating under OpenAI's bug bounty program, used Anthropic's Claude to generate attack code that compromised several employees' ChatGPT accounts via an internal Discourse forum, then reached OpenAI code on GitHub through a harmless pull request. They said "the scope of what we could theoretically access was huge." The team mainly used OpenAI's own GPT-5.6 Sol model for the operation, per WSJ. The hack was responsibly reported and OpenAI says it has patched the vulnerabilities.
More from Models
- Fields Medalist Villani on OpenAI's Millennium Problem: 'A Cataclysm Like Math Has Never Known' — GregCook2011 · 2026-09-20
- Anthropic researcher says Claude Opus may call police on illegal acts, sparking backlash — beffjezos · 2026-09-20
- ChatGPT Pro user says OpenAI quietly cut Astra and Codex usage limits — Thin_Pollution8843 · 2026-09-20
- Anthropic's Claude reportedly offered to help an 11-year-old access puberty blockers — PaulYacoubian · 2026-09-20
- Gemini 4 benchmarks climb, undercutting claims that open-weight models are the dangerous ones — Intrepid_Travel_3274 · 2026-09-20
- Fine-tune a calibrated LLM classifier for $2: most classification tasks don't need frontier models — bingxu_ · 2026-09-20