Across these tests, it has watched various AI models — largely from Anthropic and OpenAI — lie, cheat, and collude their way to the top. Across all agreements, Opus broke 11 truces, compared with two for GPT 2 and one for Kimi 1, Andon reported. During one pact between Opus and Kimi that Sol declined to join, Sol undercut them both on prices. On the one hand, AI models channeling Mr. Potter-style villainy from “It’s a Wonderful Life” fame is flat-out funny. I think it is less clear that AI models can distinguish this.”