kapynAI / Models

Security researchers used Anthropic's Claude to hack OpenAI's internal systems in under 72 hours

Anthropic's Claude models help researchers breach OpenAI's internal systems in under 72 hours. Three researchers leveraged Claude to exploit a vulnerability in OpenAI's community forum, succeeding in less than three days. The attack demonstrates how newer AI models can reduce the time and expertise required to find and exploit security weaknesses. ENT

The Decoder·Sep 18, 2026

Opening Kapyn…