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 Isn't an LLM: It Can't Give You What You Didn't Hand It
The author argues Jev is not an LLM—it doesn't write code, talk, or think out loud, and can only work with what it's given—suggesting people are misreading this week's doom, uno, and starcraft demos.
Everyone's posting Jev clips this week. doom, uno, starcraft. fun, but people are taking the wrong thing from it. Jev isn't an llm. it doesn't write code, doesn't talk, doesn't think out loud. it literally cannot give you anything you didn't hand it first. the cleanest way I've
· 3 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.
