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.
Mutable Models and Live LoRA Adapter Swapping for Jev-class Models
The author continues work on mutable models and live LoRA adapter swapping applied to Jev-class (Kev) models, discussing the interaction between the mutable model on ANE (Kev) and a GPU-resident LLM (Qwen 3.8 27B-Splash).
Continuing my work with mutable models + live LoRA adapter swapping applied to Jev-class (Kev) model. The following talks through the current use case and interaction between the mutable model on ANE (Kev) and the GPU resident LLM (Qwen 3.8 27B-Splash). --- The model writes
· 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.
