Jev by @typesafeai is now on OpenRouter, in beta. Jev is a System One model. Instead of generating text, it takes your app's state plus a typed question and returns a typed decision with a probability attached. There is no JSON prompting, parsing layer, and nothing to validate Show more
Jev 1.13 Jaggedness
A maintained list of jev-1.13's known failure modes, literal reading, unreliable counting, dates as text, indirection, context rot, and contradictory criteria, each with a guardrail.
- Category
- Practices & Patterns
- Published by
- TypeSafe AI
- Author
- —
- Added
- 2026-09-20
Tagsofficialdocsevaluationconfidencestate
Highlights
- Counting is unreliable and error grows with size: count in code, one question per item.
- Dates are read as text; extract components with Choice and compare or order them in code.
- Score levels are weak at numeric calibration, so don't interpolate an exact magnitude between levels.
- Structural invariants do not hold: complementary probabilities can sum past 1 and the same question can disagree across primitives.
Quickstart
python
result = client.system_one(
{"items": items},
{
f"item_{i}": Noul(instructions=f"Is `items[{i}]` the name of a fruit?")
for i in range(len(items))
},
)
count = sum(result.nouls[f"item_{i}"].noul > YES for i in range(len(items)))Watch out
The list is reviewed periodically rather than continuously, so treat it as a starting checklist and add the failure modes your own evals find.
More like this
How to shape what Jev evaluates: a string, a named object, or an array of messages. Every question in a request sees the same state and is evaluated independently.
Practices & Patterns#official#docs#state
Official
Rate content against 2 to 10 ordered levels. Returns a probability-weighted score that can land between levels, per-level probabilities, and confidence, with the arithmetic left to code.
Practices & Patterns#official#primitives#score
Official
Why TypeSafe trains decision models with RLCD instead of RLHF: calibrated probabilities where 0.2 outcomes happen about 20% of the time, and the case for machine-to-machine automation.
Sites & Guides#official#docs#evaluation
Official
From the community
Posts from builders shipping with Jev right now.
Jev lands on OpenRouter
700 leads scored for $0.09
JEV is INSANE. We gave it 700 high-intent leads and personalised outreach messages. In 40 seconds, it predicted how each message would perform, assigned a confidence score and detected lead-message mismatches. All for just $0.09. JEV can also score leads, analyse buying Show more