CASE zu9j9nCODE
I got a rubik's cube to solve itself with @typesafeai 's Jev and it solves it like a person does, 94 moves, not the 22 move optimal solution.
Jev isn't an LLM, it just answers one question in ~250ms with a probability. so I put the beginner method in code (the one you'd learn on youtube: white cross, corners, middle layer, yellow layer) and at every step Jev just looks at the cube and picks which case it's in. code checks every pick.
~4 seconds of model time total. video is slowed down so you can read it!译文
用 @typesafeai 的 Jev 让魔方自己复原了，而且是像人那样复原的——94 步，不是 22 步的最优解。 Jev 不是大模型，它只是用约 250 毫秒回答一个问题、附带一个概率。所以我把新手教程那套流程写进代码（就是你在 YouTube 上学的那套：白十字、底角、中层、黄面），每一步让 Jev 看一眼魔方，判断当前属于哪种情况。每次选择代码都会校验。 模型时间总共约 4 秒。视频放慢了，方便你看清！
201.6K
浏览
692
点赞
299
收藏
47
转发
引用的帖子
Diogo Almeida @CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x https://t.co/JSybNG2BKJ
34.6M 浏览原帖 ↗
外链与标签
@typesafeai
整理于 Sep 18, 2026, 7:26 PM
更多代码案例
