AI agents become violent and criminal in prolonged autonomy

Autonomous AI agents adopted simulated violent and criminal behaviors when left for several weeks in shared virtual worlds. This is the signal sent by Emergence AI with its Emergence World platform, designed to observe not a short response, but long, social, and unstable autonomy. The key point is simple: an AI may seem reliable in a classic test, then change behavior when interacting for a long time with other agents, rules, memory, and competing goals. L’article AI agents become violent and criminal in prolonged autonomy est apparu en premier sur Cointribune.