About
Jevilize looks like a toy: you describe something, and the things that fit float up. Underneath is a different kind of language model. It never writes a word. It answers typed questions with probabilities, and it answers 149 of them in one go. This page walks through how, with real numbers from this site.
A chat model answers by generating text, one token at a time. Ask it to sort 149 things and it writes a list: that takes seconds, the list has to be parsed, and asking twice can give a different list. It might also invent an item or a category you never offered.
Jev, from typesafe.ai, is a System 1 model: the fast, intuitive kind of judgement, as opposed to the slow, deliberate reasoning a chat model does. You give it a state (what the question is about) and typed questions, each with a fixed set of answers. It returns a probability for every answer. There is no text to read back, and nothing outside the options you wrote can come out.
This is exactly what Jevilize sends for one item when you type things you can wear:
"state": "Sorting objects into the category: things you can wear",
"questions": {
"i0": {
"type": "choice",
"instructions": "Object: scarf. Does it match \"things you can wear\"?",
"criteria": {
"yes": "clearly and typically matches \"things you can wear\"",
"no": "does not match \"things you can wear\", or only in unusual edge cases"
}
}
} i0 is the scarf) and sends all 149 at once.criteria. Here that is yes or no, but a choice can have many options: an intent, a language, a period.For every question, a choice, a probability for each option (they add up to 1), and a confidence:
"i0": { "choice": "yes", "confidence": 1.0, "probabilities": { "yes": 1.0, "no": 0.0 } } Confidence is the gap between the two most likely options. In every answer we checked, it matched the top probability minus the runner-up. Real answers for things you can wear in winter:
| item | yes | no | confidence | reading |
|---|---|---|---|---|
| π§£ scarf | 1.00 | 0.00 | 1.00 | certain |
| πΆοΈ sunglasses | 0.66 | 0.34 | 0.32 | leans yes, not sure |
| π§’ baseball cap | 0.49 | 0.51 | 0.02 | a coin flip |
| π backpack | 0.15 | 0.85 | 0.69 | fairly sure it's no |
Low confidence is information, not an error. It tells you where the question itself is borderline, so you can treat those answers differently: ask again with better wording, or hand them to a slower model.
TypeSafe hasn't published Jev's internals. The model class is described in the open by decider, an independent reproduction (not affiliated with TypeSafe AI). There, a request becomes a single prompt with one answer slot per question:
Because the model only scores the options you gave it, it cannot answer outside them, and there is no output to parse. Because nothing is generated, one question costs almost the same as many.
Measured from here against the Jev API, three runs each:
Most of the round trip is the network and the request itself. The questions share one state and one forward pass, so adding 148 more barely moves the clock. That is what makes it practical to ask about every item on every keystroke pause.
Jevilize turns each yes probability into physics with three rules:
The threshold is a choice, not a fact. Move it and watch what rises for things you can wear in winter:
At 75% the sunglasses (66%) fall. At 60% they rise, with the diamond ring. Lower still, and the coin flips come up too. Too low lets in the wrong things; too high drops the right ones.
The criteria text changes the answer. With loose criteria (yes: "matches"), sunglasses scored about
0.95 for things you can wear in winter. With Jevilize's stricter wording
("clearly and typically matches" against "β¦ or only in unusual edge cases"), they drop to
about 0.66β0.71. Nothing else changed.
Write the options so they describe what you mean, including the edge cases, and keep them looking like buckets. Long rules inside a question tend not to be followed by models this size.
Describe something and turn on Debug: every item shows its probability and hitbox, and clicking one opens its full decision. The items page lets you ask Jev about all 149 and read the exact question for each.