Jev glossary
Evaluation & TrainingCounting
Unreliable counting
Jev does not count reliably (characters, occurrences, or list items), and error grows with the size of the thing counted.
- Category
- Evaluation & Training
- Also known as
- Counting
- Reading time
- 1 min
- Related terms
- 4
- Directory entries
- 1
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The model recognizes the shape of an answer rather than tallying. Before asking a counting question, the docs suggest asking why a model is needed at all: if a regex or parser can find the unit, the count belongs in code.
When the count does need judgment, iterate in code over candidates, ask one Noul per item, and sum the answers yourself: the pattern the jaggedness page demonstrates with a fruit-name count.
Tagslimitationsdesign
Related terms
Definitions that connect to this one.
JaggednessThe documented set of jev-1.13 failure modes (literal reading, counting, dates, indirection, context rot), each with a guardrail.Evaluation & TrainingNoulThe yes/no primitive: one probability from 0 to 1, where the value is the answer and no separate confidence is returned.PrimitivesDates as textJev reads dates as strings, not ordered quantities; extract components with Choice and do the ordering and math in code.Evaluation & TrainingAtomic questionA question that asks one specific, well-scoped thing, the kind of judgment a knowledgeable person makes in a few seconds.Core Concepts
From the Jev directory
Directory entries that go deeper on this term.
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.
Jev Practices & PatternsDocs#official#docs#evaluation
Official
From the Jev AI model community
Posts from builders shipping with Jev right now.