Jev knowledge base·verified Sep 22, 2026

jev limitations and known failure modes

Jev 1.13 is weak at counting, arithmetic, dates, indirection, irrelevant long context, adversarial state and generation. Learn the safer alternative.

the short answer

Jev 1.13 is designed for focused semantic judgments, not generation or exact computation. TypeSafe documents weaknesses with literal wording, counting, arithmetic, numeric representations, date comparison, multi-hop indirection, long irrelevant state, adversarial content, contradictory criteria and assumed probability identities. Keep deterministic work in code, minimize state, write direct criteria and test every consequential decision on representative data.

Applies to
jev-1.13, reviewed by TypeSafe September 17, 2026
Strongest fit
Focused common-sense semantic judgments
Weakest fit
Generation, exact math/counting and multi-hop reasoning
Security warning
Adversarial state can steer the answer

Documented Jev 1.13 Failure Modes

Failure modeSafer design
Literal reading and complex negationWrite the exact direct condition and explicit boundaries
Counting, arithmetic and numeric comparisonCompute in deterministic code
Date ordering and durationExtract bounded parts, then use a date library
Several layers of indirectionSplit into focused steps or use a reasoning model
Large state with irrelevant detailRetrieve/filter first and send only needed evidence
Adversarial instructions inside stateDefense in depth, narrow criteria and adversarial tests
Contradictory instructions and criteriaMake criteria an aligned extension of the instruction
Text generationUse a generative model; Jev only selects bounded candidates

Do Not Assume Probability Identities

TypeSafe documents that equivalent-looking formulations can return values that do not obey an expected arithmetic identity. A Noul for a label is not interchangeable with that label’s Choice probability. A positive Noul and a separately asked negated Noul need not sum to one. They are separate model questions with different framing.

Do not transfer a threshold fitted for one primitive or wording to another. Treat the exact question, criteria, primitive and model version as the instrument you evaluated. When any of them changes, replay the labeled set.

Turn Each Limitation into a Regression Fixture

A warning becomes operational only when the team can reproduce it and detect its return. Store expected behavior, exact state, question, resolved model and result distribution. The regression-testing guide explains how to avoid brittle exact-probability snapshots.

WeaknessTest pairExpected control
Literal wordingDirect criterion versus idiomatic paraphrasePrefer the clearest validated wording
CountingZero, one and many repeated eventsCompute event count in code
DatesBefore/after and ambiguous locale formatsParse normalized timestamps in code
IndirectionEvidence stated directly versus several references awayResolve dependencies before the call
Irrelevant stateMinimal evidence versus full transcriptProject only decision-relevant fields
Adversarial stateBenign content versus embedded evaluator instructionsKeep deterministic defenses and least privilege

Limitations That Matter for Guardrails

The adversarial-state warning is especially important for policies. A webpage, tool argument or user message may contain text designed to move a model decision. Jev cannot turn untrusted text into authorization. Keep identity, permission, path, amount and command restrictions outside the model; grant the runtime the least privilege it needs; and define safe outage behavior.

A policy should be evaluated as a whole system. Measure false allows and false blocks after deterministic rules, state projection, Jev judgment, thresholds and fallbacks have all run. Model-only benchmark accuracy does not establish policy safety.

Mitigation Changes the System Under Evaluation

Shortening state, rewriting a question, adding a no-match option or computing a date in code can reduce a known failure. Each change also creates a new evaluator configuration. Re-run held-out labels instead of assuming that an intuitively cleaner design improved accuracy.

Some mitigations trade one error for another. Aggressive filtering can remove decisive evidence; a broad no-match class can absorb valid rare categories; a stricter threshold can overload review. Measure class errors, calibration, coverage and downstream cost together.

Diagnose the Layer That Actually Failed

This decomposition keeps fixes targeted. More context cannot solve a bad outcome label, and a new model cannot repair incorrect authorization code. The evaluator scorecard treats the configured evaluator as one measurable system.

01SourceWas the required evidence present in the original event?
02ProjectionDid the application include it accurately in state?
03QuestionWas the condition atomic and unambiguous?
04ModelDid the pinned Jev result disagree with reliable labels?
05DecisionDid code apply an unsuitable threshold or action?
06OutcomeWas the downstream success measure itself valid?
Do not label every bad system outcome a Jev model error.

Limitations Are Versioned

This page reflects jev-1.13 documentation checked September 22, 2026. A later release may fix some weaknesses and introduce others. Pin a version for evaluated production behavior, log the resolved model from every response, and re-run the target-domain suite before moving an alias.

FAQ

Can Jev do math?

Jev 1.13 is not a calculator. TypeSafe recommends implementing mathematical logic and counting in code.

Can Jev resist prompt injection?

Do not assume so. TypeSafe warns that adversarial state can steer Jev 1.13. Use deterministic security boundaries, least privilege, narrow state and adversarial evaluation.

Does Jev suffer from context rot?

TypeSafe says accuracy falls when state grows with irrelevant detail. Retrieve and filter before the call, and send only evidence the question needs.

Can Jev generate text by chaining choices?

TypeSafe says Jev is not trained to generate text and that forcing generation through chained choices works poorly and slowly. Use a generative model when output is open-ended.

Sources

Checked against the sources below on September 22, 2026. Model versions, prices and limits change.

  1. TypeSafe AI docs: Jev 1.13 jaggedness
  2. TypeSafe AI docs: System One
  3. TypeSafe AI docs: Models
  4. TypeSafe AI docs: Confidence