I rebuilt my job crawler with Jev. The task: start at a company's official homepage, find Careers, and identify jobs that match my profile. Before, with an LLM: ~5 minutes. After, with Jev: just over 20 seconds in my test. Every company organizes its website differently. Jev Show more
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
- 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 directory
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.
Practices & PatternsDocs#official#docs#evaluation
Official
From the community
Posts from builders shipping with Jev right now.
A job crawler that reads careers pages with Jev
700 live ads in 40 seconds
jev is an insanely cool product Saw a post about jev and decided to check it out This thing is straight up gold whoever built it is a genius jev is the future Scanned over 700 live ads in 40seconds flat, and it cost me just 4 cents. If you're in marketing, this kind of crazy Show more
1,891 ads in 19 seconds
ESTA HERRAMIENTA ACABA DE ROMPER TODO EL MERCADO DEL AD SPY Maxfusion ha cogido JEV, el modelo nuevo de TypeSafe, y le ha metido la ad library entera de una marca → 1.891 anuncios clasificados → 19 segundos → 0,12 $ Y no es un resumen: cada anuncio etiquetado por etapa del Show more
JEV makes competitor research feel like a cheat code We fed it Resilia’s ad library and it classified 1,891 ads in 19 seconds for $0.12 Customer journey stage, ad style, and a full account deep dive Coming soon to the maxfusion MCP
Game levels generated in real time
Jev can generate game levels in real time. Faster and cheaper structured output could be a big deal for game dev!
900 images in 40 seconds
Made myself a little image classifier with OCR + Jev It was able to categorise ~900 images in 40 seconds Pretty cool
Intent-based search in Gmail
Jev is really good at intent-based search! How it looks in Gmail: (for a huge inbox you'd prob let semantic search / embeddings pull first but still much better experience)
@dabit3
Another crazy @typesafeai Jev example: Predictive spreadsheets Spreadsheets recalculate numbers, not meaning. Jev reads intent. Type "Urgency" at the top of a column and, as you type, it figures out you want each row rated from "no follow-up needed" to "urgent" in ~100 ms.