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 Decision Models Face Training Data Cutoff Challenge
The post notes that decision models like Jev must solve the training data cutoff issue, otherwise decisions rely on information over six months old, which matters greatly for real-time data scenarios like marketing and investing.
Decision models like Jev have a real challenge to solve with training data cutoff. Otherwise the decisions rely on >6 month old information. This is a big deal for places where decisions need realtime data (marketing, investing, etc). For example, Jev estimates odds Navier
· 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.
