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 Approval Policy as a Prompt: Verdicts at Inference Time
Explains that Jev receives a tool's approval policy, description, and invoked params at inference time and returns a verdict; approved calls start immediately while denied calls run after codegen like normal PTC.
The approval policy is a prompt. Jev is provided the tool's approval policy, along with its tool description and invoked params at inference-time and returns a verdict. Approved calls start immediately and denied calls run once the codegen is complete just like normal PTC.
· 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.
