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.
Building a Reranker on Jev: Calibrated Confidence as a Prune-and-Gate Signal
Sharing experience building a reranker on Jev: a real probability turns the score into a prune-and-gate signal rather than just a rank, and discussing extending calibrated confidence to primitive types.
Extending calibrated confidence to primitive types is the natural next step -- we saw the same shape building a reranker on Jev: a real probability turns the score into a prune-and-gate signal, not just a rank.
· 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.
