Model Releases
Researchers used Claude to hack OpenAI
In September 2026 Hacktron AI researchers used Anthropic’s Claude to exploit a flaw in OpenAI’s community‑forum hosting configuration, giving them access to an employee’s ChatGPT account and confident
In September 2026 Hacktron AI researchers used Anthropic’s Claude to exploit a flaw in OpenAI’s community‑forum hosting configuration, giving them access to an employee’s ChatGPT account and confidential software data. The breach occurred under a formal bug‑bounty program that paid the team $6,500 for uncovering vulnerabilities before malicious actors could exploit them. The incident highlights the growing risk that rival AI tools can be repurposed to identify and leverage security weaknesses in other leading AI organizations.
Related
Source: Ars Technica | 2026-09-18