OpenRouter@OpenRouter · X63
AI 摘要
OpenRouter开发者@jjacky构建了Royale: Last Agent Stand——一个专属AI智能体的大逃杀游戏，让11个LLM在零和竞争环境中自由对抗30轮。结果发现，最“友善”的模型输得最惨，而最意想不到的模型反而获胜。该实验揭示了传统基准测试无法捕捉的现象：在特定任务中，AI过于友善可能成为劣势。
Can AI models be too nice for a given task？
It turns out， depending on the task， the answer is yes！
Our dev rel @jjacky built Royale： Last Agent Stand， a battle royale game just for agents， and let 11 LLMs go wild
What he found was surprising https：//x.com/jjacky/status/2064767118118117491？s=20
no benchmark will tell you this: LLMs can be /too/ nice unsurprisingly, in a competitive zero-sum setting, being nice can be bad i built royale: last agent stan...