DevelopmentNewSources: 5 sources
Researchers breach OpenAI systems using Anthropic models
The Financial Times reports that a security research company breached OpenAI's systems using AI tools developed by rival Anthropic. Claims are as reported; this summary makes no determination about accuracy or significance.
Coverage
- Security researchers used Claude to help them hack into OpenAIThe Verge ·
- Researchers used Anthropic’s Claude to hack into OpenAITechCrunch ·
- Researchers used Claude to hack OpenAIArs Technica ·