On September 18, 2026, US cybersecurity researchers successfully hacked OpenAI's systems with assistance from Anthropic's Claude chatbot in what was framed as an 'ethical' security demonstration. Researchers noted the potential 'scope of what we could theoretically access was huge,' highlighting vulnerabilities in AI company infrastructure.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
US cybersecurity researchers who conducted hack say ‘scope of what we could theoretically access was huge’ Cybersecurity researchers have hacked into OpenAI with the help of Anthropic’s Claude chatbot, in the latest example of security issues at the company. A team at a US-based startup compromised a number of OpenAI employees’ ChatGPT accounts, starting a process that enabled them to access their
this outlet adds: theguardian, technology, megafirms, well, chimps, managing, stockpile, nuclear
OpenAI 'ethically hacked' with help of Anthropic's Claude chatbot L: https://www. theguardian.com/technology/202 6/sep/18/openai-hacked-anthropic-claude-chatbot C: https:// news.ycombinator.com/item?id=4 9755468 posted on 2026.09.18 at 11:07:08 (c=0, p=3)
OpenAI ‘Ethically Hacked’ with Help of Anthropic’s Claude Chatbot https:// packetstorm.news/news/view/435 91 # news