Ars Technica
Researchers used Claude to hack OpenAI
Cyber researchers broke into OpenAI using its key rival Anthropic’s software, highlighting vulnerabilities in the ChatGPT maker’s security as leading AI companies face mounting scrutiny over safety. A small cyber security group gained…
View original source — Ars Technica ↗
Related stories
TechCrunch
TechnologySep 18, 2026 · 1 min
Researchers used Anthropic’s Claude to hack into OpenAI
TechCrunch
CNA
BusinessSep 18, 2026 · 1 min
Researchers used Claude to breach OpenAI's internal systems
CNA
The Guardian
BusinessSep 18, 2026 · 1 min
OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot
The Guardian
Straits Times
ScienceSep 18, 2026 · 1 min
Researchers used Claude to breach OpenAI’s internal systems
Straits Times