Jev glossary
Evaluation & Training
Contradictory criteria
When instructions and criteria ask for different things, accuracy drops; treat criteria as an extension of the instruction.
- Category
- Evaluation & Training
- Also known as
- None
- Reading time
- 1 min
- Related terms
- 4
- Directory entries
- 1
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The clearest example in the docs is a Noul whose true maps to no and false to yes, which performs worse than the natural phrasing. Clear, human-readable alignment between instruction and criteria is what the model was trained on.
The guardrail is to align the two with precise language and to prefer question shapes an average person could read and answer consistently.
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 & TrainingCriteriaThe possible answers for a question: a map of options for Choice, an ordered list of levels for Score, or true/false for Noul.PrimitivesInstructionsThe field that states what a question should judge; accepts a string, an object, or an array for extra structure.PrimitivesLiteral readingJev answers the question you wrote, not the one you meant; scoping words, negations, and implied conditions are read at face value.Evaluation & Training
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.