返回探索

为 Jev System 1 模型构建开源 harness 并玩 Mario

开发者利用周末构建了 SystemOneHarness,一个面向 TypeSafe AI 的 Jev 等 System 1 模型的开源 harness,并通过教它玩 Mario 进行测试,强调无思维链、无反思、每秒 60 次决策。

Weekend plan: rest. Actual weekend: built SystemOneHarness, an open source harness for System 1 models like #Jev from @typesafeai. Then, to test it, taught it to play Mario. No chain of thought. No reflection. Just vibes at 60 decisions per second. It's better than me now, which

· 2 次赞在 X 打开