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.
What is Jev: A Classification/Decision Model for Software
Jev is described as a classification/decision model for software: instead of conversing, state plus fixed questions go in and typed probabilities come out. The author asks if anyone has wired it into interesting applications.
What is Jev (JEV)? Think of it as a classification/decision model for software. One doesn't converse with it like an LLM. Instead, State plus fixed questions go in and typed probabilities come out. Anyone wiring Jev into anything interesting yet?
· 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.
