OpenJev Runs a Jev-Style Decision Model Entirely in Your Browser
OpenJev is a live, local experiment that runs a decision model in your browser with no backend. It compares two paths on the same GPU: reading choice logits directly versus generating JSON probabilities token by token. Choose MiniCPM5 2B, Qwen3 0.6B, or Qwen3.5 4B, load quantized weights via WebGPU, and time each method yourself. The published Jev scores 88.3% TypeSafe; the browser builds are quantized and not claimed to match it.
Direct scores are a softmax over only the displayed option tokens. They are not calibrated confidence and do not include every answer the model might prefer.
- prodigycorp
These one shot vibecoded sites are always a complete visual headache. Endless clutter, pointless filler text all over the place, and zero regard for actual usability.
- mmastrac
If you want to try a _legit_ Jev implementation that matches (at least in my evals), the vLLM patch to turn DiffusionGemma into Jev is available.
On my DGX Spark I get very similar latency numbers, and it matches my evals + or - a few points on each test (DG wins some, Jev wins some, both show low confidence when wrong).
I ran the same evals against a Qwen36 and it clearly lost to both of them, so you are leaving both knowledge and instinctual reasoning on the table with any smaller models, FWIW.
- wuhhh
I don't understand how this is different from oai "structured output" (and whatever the similar paradigm was on Sonnet ~3.7 back then) which everyone moved on from. On their gh they say:
"Jev is TypeSafe's closed service for runtime-defined semantic decisions. This project reproduces that interface pattern with open models; it does not reproduce Jev's undisclosed model or training"
As someone else pointed out it isn't actually Jev... can someone enlighten me
- wg0
Important - Jev is way too different, the greatest innovation are its speed and that it is guaranteed to NOT generate a token from a given set of tokens hence you can drive state machines intelligently.
- kul_
Is it only me or do others also find LLM generated websites so off-putting?
- lucfranken
Jev is such a different approach where you have to be specific about what you want and which options are open. Really interesting how those things evolve in usable features for people.
Also with this example the speed of new launches based on a launch is just incredible.
- mohsen1
There is an open PR for VLLM to do this via DefussionGemma
- mukundesh
I am not sure how this is JEV, but just a llm following the JEV api, as it is using standard LLMS. The main contribution of JEV is not the API but the model itself. Can someone please explain ?