Jev versus text-generating models
Jev does not generate free-form text. A side-by-side video compares parallel decision-making with token-by-token text generation.
Diffusion LLM May Suit Jev-Style Fast Decision Models
The post notes that Jev cannot generate continuous mouse-click coordinates by enumerating options, while Diffusion LLM offers stronger expressiveness at similar inference speed, and predicts a future 50 mspt Computer.
woc一语点醒梦中人，Google果真有高人在的，Diffusion LLM才是最适合Jev这种快速决策模型的架构，而且可以在保持推理速度相同的同时有比Jev这种模型更强的表达能力（比如要生成鼠标点击动作，Jev是没办法通过枚举选项生成连续点击坐标的，但是DLLM就可以） 过一段时间说不定就会有50 mspt 的Computer
· 0 likesOpen on X
More like this
Pricing, evaluations, and the name Jev
The launch thread explains code-and-AI workflow evaluations, the input price announced at launch, and free output tokens.
Jev Model: Decision-Making Probability Generation, 200× Faster and 400× Cheaper Than LLMs
This model is built for decision-making rather than text generation, outputting probabilities for each option in parallel instead of token-by-token responses. The author shares a simplified comparison of normal LLMs versus this Jev model.
