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.
CLM as a More Generalized System One Model
The author suggests CLM is not the next generation of Jev, but rather a more generalized System One model for agents; its core is not just returning Noul/Choice/Score, but goes further (text truncated).
This is pretty big. Rather than being the next generation of Jev, it feels more like "a more generalized version of the System One model for agents." The most important thing is that CLM isn't just a model that returns Noul / Choice / Score; at its core, it's a model that
· 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.
