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: Defining Valid Outputs Before Inference
Introduces Jev's approach of defining valid outputs before inference, contrasting with the common flow of generating text then stripping markdown, parsing JSON, and validating schema.
JEV DELETES THE DUMBEST PART OF AI CODE. - Generate text. - Strip the markdown. - Parse the JSON. - Validate the schema. - Retry after the model adds a poem anyway. Jev starts from the opposite assumption: the valid outputs are defined before inference. State goes in. A typed
· 1 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.
