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's System One inference runs locally on iPhone and Mac
The post explains that Jev's popularized System One inference runs locally on iPhone or Mac via a Core AI implementation, suited for repeated on-device decisions like flagging utterances needing replies, checking pastes, and vetting agent commands.
System One inference, the kind Jev made popular, runs on an iPhone or a Mac (a Core AI implementation). It suits on-device use: telling which utterance needs a reply, checking a paste, vetting an agent's command are decisions made locally, many times over. https://github.com/john-rocky/coreai-kit/blob/main/docs/SYSTEM_ONE.md…
· 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.
