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: An AI That Doesn't Write, Only Returns Classification Probabilities
Jev doesn't generate text answers; it returns only urgency, category, and probability, at 0.2 seconds per item. Splitting one question into five smaller ones raised accuracy from 62.6% to 95.0%.
文章を書かないAIが出ました。Jevというやつです。 質問に言葉で答えず、急ぎかどうか、どの分類か、その確率だけを返す。書かないから速くて、1件0.2秒。 面白いのはここからで、1問でざっくり聞くと精度62.6%。同じデータを5つの小さな問いに割ったら95.0%まで上がりました。
· 6 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.
