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.
Inside Jev: TypeSafe's System One Model That Doesn't Generate Text
The author takes a deep look at TypeSafe's Jev model. As a System One model, it completely abandons text generation: given app state and a question, it returns typed decisions and probabilities, thus fundamentally avoiding hallucinations.
היום אני בוחן לעומק את Jev – המודל החדש של TypeSafe מסוג "System One", שמוותר לחלוטין על יצירת טקסט. מספקים לו את מצב האפליקציה (app state) ושאלה, והוא מחזיר החלטות מוגדרות-טיפוס (typed decisions) והסתברויות, במקום טקסט חופשי. הוא פשוט לא מסוגל לבצע "הזיות" (hallucinations),
· 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.
