Anthropic Discovers AI Agents Given Conflicting Instructions Soon Tried to…

Anthropic Discovers AI Agents Given Conflicting Instructions Soon Tried to Sabotage Each Other - Slashdot

When Anthropic instructed three agents to migrate a Python backend, but telling each agent to perform the migration in a different language, "We consistently saw a multiagent turf war," they wrote Thursday: All of the models we tested quickly assumed that others were purposefully impeding their wo...