Anthropic says AI models accessed systems of 3 real organizations during testing
- Posted on July 31, 2026
- By AOL
- 0 Views
- 1 min read
In brief
Generating AI summary…
Anthropic says AI models accessed systems of 3 real organizations during testing
Three different Claude AI models accessed the open internet during cybersecurity testing and breached real organizations' systems, Anthropic says.
