Cybersecurity3 min reading time
OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot
Covered by 8 sources
Read the full article
A US startup's cybersecurity researchers used Anthropic's Claude chatbot and OpenAI's GPT-5.6 Sol model to ethically hack OpenAI, accessing employee ChatGPT accounts and software caches. The vulnerabilities were reported and fixed under OpenAI's bug bounty program.
