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.
Generating Sentences Step by Step with Jev Probabilities
The post explains that putting Jev in a loop and selecting the most likely word step by step can generate sentences, noting you can sample from high-probability words.
Did you know that, if you put jev in a loop, and simply select the most likely word over a vocab space step by step, you can make jev generate sentences? Since jev returns probabilities, you can actually get quite a few words with high probabilities, and if you sample from those
· 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.
