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.
How Jev Works: An Encoder-Style Classifier
This post offers a simple way to think about Jev: it behaves like an encoder-only transformer with a classification head. State and options go in, probabilities come out, in a single forward pass—no text generation or parsing.
Everyone is calling Jev a new kind of AI model. Here's the simpler way to think about it: Jev behaves exactly like an encoder-only transformer with a classification head. State goes in. Options go in. Probabilities come out. One forward pass. No text generation, no parsing, no
· 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.
