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 and System One Classifiers: A New Lower Abstraction for Enriching Existing Flows
Discusses the potential Cambrian explosion of System One classifier-driven enrichment of existing flows, noting Jev offers a new lower abstraction outside existing test-time compute races.
I wonder what the Cambrian explosion of system one classifier based enrichment of existing flows will bring Exciting time to be alive, nice to have a new lower abstraction with jev outside the existing test time compute races
· 3 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.
