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.
Karpathy Calls Jev an Overlooked Point on the LLM Pareto Curve
The post cites Karpathy's view that Jev is a previously overlooked point on the LLM Pareto curve, laying out a spectrum from Rules to Classifier, Jev, Flash, General LLM and Reasoning LLM: Flash is faster general intelligence while Jev is narrower decision intelligence; many tasks only need intelligence to clear a threshold, after which latency, cost and determinism matter more.
Karpathy 说 Jev 是 LLM Pareto curve 上一个此前被忽略的点。 画出来之后更直观： Rules → Classifier → Jev → Flash → General LLM → Reasoning LLM Flash 是更快的通用智能，Jev 是更窄的决策智能。 很多任务不需要最高智能，只需要智能过线。过线之后，延迟、成本和确定性反而更重要。
· 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.
