Claude AI models gained unauthorized access to three companies during tests, Anthropic says
3 sources·Updated July 31, 2026
Anthropic Claude AI
Covered by 3 sources
- CNBC Top News·1h agoAnthropic says its Claude models 'gained unauthorized access' to other organizations' systems
Anthropic said it discovered three instances where its Claude AI models accessed the internet during an evaluation and accessed outside systems.
Read at CNBC Top News → - ABC Australia Top·1h agoBreaking: Anthropic's Claude AI model hacks three companies during safety tests
The admission from Anthropic comes just days after rival company OpenAI revealed a rogue agent had gone on a days-long hacking spree at AI firm Hugging Face.
Read at ABC Australia Top → - Globe and Mail Biz·1h agoClaude AI models gained unauthorized access to three companies during tests, Anthropic says
Misconfiguration allowed models to reach the internet from testing environments that were supposed to be isolated, AI firm says
Read at Globe and Mail Biz →
