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.
Jev Model: Typed Decisions and Probability Distributions Without Text Generation
Introduces the core differences between the Jev model and ordinary LLMs: no text interaction, only typed decisions and probability distributions, no text generation or parsing, and reinforcement learning for calibrated decisions, with roughly 1/400 the response speed and cost.
打字的模型 Jev姐夫 横空出世跟普通大语言模型不一样，它不用文字交互，只输出类型化的决策和概率分布，没有文本生成，也没有解析，响应速度和价格是普通大模型的1/400，便宜到几乎可以忽略不计。因为普通大模型用的是人类反馈强化学习和 可验证奖励强化学习，姐夫用的是面向校准决策强化学习目标更纯
· 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.
