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.
Unmasking Jev's Architecture with 10,000 API Calls
An analysis of Archer Hume's experiment on how Jev outputs probabilities without generating text, covering shared state, isolated branches, and probability calibration, while distinguishing observations from speculation.
一个人用 10000 次 API 调用，扒出了 Jev 的底层架构【Jev03】 不生成文字，Jev 怎样直接给出概率？这期解读 Archer Hume 的实验，拆开看共享状态、隔离分支与概率校准，也讲清哪些是观察、哪些仍是推测。 原文： https://archerhume.com/posts/jevs-architecture-unmasked… #Jev #AI
· 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.
