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 Is Just a Classifier: A Conversation on Multi-Tool AI Apps
The author notes Jev is just a classifier, not magic, but its launch sparked a needed conversation about using multiple tools instead of a single frontier model for AI apps.
Yes, Jev is just a classifier. No, it’s not magic. But I think its launch has sparked a conversation we needed to have about using more than one tool to build AI applications, rather than relying on a single frontier model for everything. We got close to Jev’s accuracy using
· 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.
