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 Auto Model Routing: Jev Classifies Work, Never Chooses the Model
Explains Jev's auto model routing design: at the start of each turn Jev classifies the work (conversation, writing, coding, analysis, extraction) and detects secondary requirements like tool usage and continuity, while model selection happens elsewhere.
We built Auto model routing with Jev, but Jev never chooses the model. That distinction is the whole design. At the start of each turn, Jev classifies the work: conversation, writing, coding, analysis or extraction. It also detects secondary requirements, tool usage, continuity
· 2 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.
