Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware
Anthropic has been conducting tests to identify issues in how AI agents interact with each other.
The post https://www.securityweek.com/conflicting-test-goals-pushed-claude-agents-to-deploy-self-replicating-malware/">Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware appeared first on https://www.securityweek.com">SecurityWeek.