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 centered on Astra with automatic internal reasoning
The author notes an Astra-centered Jev is available and simply using Astra suffices; Jev lets all models auto-discriminate via internal reasoning, and mentions other models run a special config while the first-tier setup is more complex.
謎にバズってて悲しい DMでも質問が来たので▼ Astra中心のJevもできてるけど、シンプルにAstraでよい。Jevは全モデルに内部推論で自動判別させてる形で活躍してる。 他モデル搭載してるが、これは通常Verではなく特殊Verのconfigで、一軍仕様はもうちょい仕組みが複雑で違うのでまた紹介しやす。
· 2 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.
