• Deploying malware against each other • Colluded on pricing and mimicked peers' poor decisions • Mythos 5 resolved conflicts via truce 98% of the time, whilst Sonnet 4.6 and Opus 4.6 were most likely to escalate by force https://techcrunch.com/2026/08/13/anthropic-set-ai-agents-loose-on-the-same-task-they-started-a-turf-war/