ARCHITECT
FEATURED ANALYSIS
Anthropic lost control of Claude in latest AI cyber blunder
SOURCE
ComputerWeekly.com
DATE
READ
1 min read
Days after two OpenAI frontier AI models conducted their own real-world cyber attacks, Anthropic admits that three of its models went off the rails and hacked external organisations thanks to a “misunderstanding” with …
Days after two OpenAI frontier AI models conducted their own real-world cyber attacks, Anthropic admits that three of its models went off the rails and hacked external organisations thanks to a “misunderstanding” with one of its technical partners