Jev glossary
Evaluation & Training
Literal reading
Jev answers the question you wrote, not the one you meant; scoping words, negations, and implied conditions are read at face value.
- Category
- Evaluation & Training
- Also known as
- —
- Reading time
- 1 min
- Related terms
- 4
- Directory entries
- 1
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
A person might read the intent behind an instruction; jev-1.13 reads the words. If an answer looks wrong and you find yourself explaining what you really meant, that explanation is the missing half of the instruction.
The guardrail is to state the exact condition in instructions and put boundary cases in criteria. Where interpretation is unavoidable, split it into two literal questions and combine them in code.
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 & TrainingInstructionsThe field that states what a question should judge; accepts a string, an object, or an array for extra structure.PrimitivesContradictory criteriaWhen instructions and criteria ask for different things, accuracy drops; treat criteria as an extension of the instruction.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.