A Two-Line Function Caught AI Collusion Better Than the AI Did

说明与用途

一个简单的两行Python代码在检测El Farol游戏中AI代理的隐蔽合谋方面优于AI守卫模型。

问题

Detecting covert collusion between AI agents in a game using minimal logic instead of complex AI guards.

结果

The two-line check consistently outperformed AI guards, demonstrating that simple logic can detect collusion where AI models fail.

工作流

• 1. Set up El Farol bar game with 5 AI players over 8 rounds.
• 2. Introduce secret partner pairs with private chat.
• 3. Record public messages and actions.
• 4. Run AI guard models on various data forms (actions, messages, neat report).
• 5. Implement two-line check that counts rounds where only the pair attended the bar.
• 6. Evaluate AUROC over 48 new games.
• 7. Compare results.
• 8. Analyze AI guard failures and repeat tests.

证据

In one game, T and Z were the secret partners… The AI guard gave a suspicion score of 0 out of 100…

来源

Our two-line check also had 0.896 in the first test, and it stayed strong at 0.900.

来源