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.
Zero-shot span-style QA in DiffusionGemma-as-Jev
The author shares zero-shot span-style questions in DiffusionGemma-as-Jev (djev), calling it a useful, non-hallucinating primitive, with performance still being tuned.
Zero-shot "span"-style questions in DiffusionGemma-as-Jev (aka djev). Still tuning performance a bit, but this is another very useful, non-hallucinating primitive.
· 11 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.
