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 vs Gemini: Structured Output Handling Test
The author widened the batch to roughly 300 questions per call. Jev answered successfully, while Gemini rejected all requests before generating anything. Input was only ~55k tokens in a ~1M-token context window, illustrating an issue in how Gemini enforces structured output.
5/7 Then I widened the batch to roughly 300 questions per call. ✅ Jev answered. ❌ Gemini rejected all 300 test requests before generating anything. The input was only ~55k tokens in a ~1M-token context window. The problem was how Gemini enforces structured output using a
· 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.
