Simon Willison details how his team took over ChatGPT accounts
paaloeye · hn · 2026-11-01
Simon Willison published "How we took over ChatGPT accounts", a detailed write-up (now on Hacker News) walking through how his team discovered and exploited vulnerabilities to take over ChatGPT accounts — a concrete account-takeover case study in AI security, covering the flaw, the exploit chain, and disclosure.
More from Safety
- 「见过最丝滑的钓鱼邮件」：账户锁定通知暗藏双重陷阱 — StewartalsopIII · 2026-11-02
- HMRC's new customer system estimated at £1.7bn-£4.4bn, dwarfing UK's £640m sovereign AI fund — birchlse · 2026-11-02
- Unpatched Linux servers with one exposed TCP port and MPTCP face full takeover — IgorCarron · 2026-11-02
- OpenAI will honor shared robots.txt so websites can opt out of AI training — rhiever · 2026-11-02
- HN Discusses Alleged Mythos-Class Anthropic Checkpoint Leak on Hugging Face — explosion-s · 2026-11-02
- Greg Brockman on how defenders can use AI to find and fix security flaws — No Priors · 2026-11-02