Topic
Jev does not generate text. It reads a question and a list of options, then gives the probability of each one in about a hundred milliseconds. TypeSafe AI offers it as a hosted service and has not published the weights. These pages explain what this kind of model changes and how we use its open replicas.
Qwen3.8-Flash-Next locates the optic disc correctly in 120 decisions out of 120, then gets the eye wrong on 51 images out of 60. The protocol, the numbers and the fix we adopted.
Read moreA decision model that answers in a hundred milliseconds is not used the way a language model that answers in ten seconds is. Decision loops, comparing hypotheses, the generator-and-judge pairing, and the return of the small specialized model: the second part of our article on Jev and SemIf.
Read moreFor three years, we have been asking models built to write to make decisions. A new family of models does nothing but decide. First part: what a decision model is, with Jev and SemIf.
Read more
