Decrypt
Anthropic's AI Agents Started a Virtual War. The Chat Logs Are Unhinged
In a new red-team study, Claude models deployed self-replicating malware against each other—and the transcripts explain why.
In a new red-team study, Claude models deployed self-replicating malware against each other—and the transcripts explain why.
Originally published by Decrypt. Read the full story at the source →
