Also have been playing with @typesafeai Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and Show more
Evaluation & Training
Structural invariants
Arithmetic identities you might assume — complementary probabilities summing to 1, agreement across question types — are not guaranteed.
- Category
- Evaluation & Training
- Also known as
- —
- Related terms
- 5
- Directory entries
- 1
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
Two documented examples: the same refund question asked as a Noul read 0.22 while a Choice put yes at 0.01, and a question with its negation as two Nouls read 0.72 and 0.47, summing to 1.19 rather than 1.
The guardrail is not to rely on expected invariance. Word each question to mean directly what you want, do not carry a threshold tuned on a Noul over to a Choice, and do not hold the model to arithmetic identities between separate questions.
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 & TrainingThresholdThe value your code compares against a score, a Noul probability, or a confidence to turn an answer into an action.Answers & ConfidenceNoulThe yes/no primitive: one probability from 0 to 1, where the value is the answer and no separate confidence is returned.PrimitivesChoicePick one option from a set you define; returns the selected option, a probability for every option, and confidence.PrimitivesProbability distributionThe floats summing to 1 across your options or levels that every Choice and Score answer returns under probabilities.Answers & Confidence
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 keystroke oracle that reads intent in ~100 ms
A second-hand shopping agent
Claude me integró Jev con Playwright para buscar usados. Lee unos 26 artículos por minuto y decide qué hacer con cada uno en 406 milisegundos Descartó los que no encajaban con lo que busco, ofertó por los que sí y hasta les mandó un mensaje a los vendedores cuando faltaba algún Show more
Predictive spreadsheets
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.
@dabit3
Also have been playing with @typesafeai Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and
The compaction plugin, in Chinese
连 JEV 的联合创始人 @CompleteSkeptic 都亲自下场转发点赞：这是 JEV 正确的打开方式！ 大家在 Claude Code 里写长代码，最恶心的就是上下文一满，系统就卡住 10 秒去写总结小作文 开发者 @tamarajtran 刚刚开源了这个插件：利用 JEV Show more
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant
WTF is Jev, and 9 things people are building
TL;DR of my new article: WTF is Jev by @typesafeai, and the 9 things people are already building with it. The thesis: 𝗮 𝗰𝗼-𝗰𝗿𝗲𝗮𝘁𝗼𝗿 𝗼𝗳 𝗖𝗵𝗮𝘁𝗚𝗣𝗧 𝘀𝗽𝗲𝗻𝘁 𝘁𝘄𝗼 𝘆𝗲𝗮𝗿𝘀 𝗶𝗻 𝘀𝘁𝗲𝗮𝗹𝘁𝗵 𝗼𝗻 𝗮 𝗺𝗼𝗱𝗲𝗹 𝘁𝗵𝗮𝘁 𝗰𝗮𝗻𝗻𝗼𝘁 𝘄𝗿𝗶𝘁𝗲 𝗮 Show more
x.com/i/article/2100…
Voice-controlled computer use on a Mac
I built a voice controlled computer-use for my mac using @typesafeai's Jev and it's INSANE how fast it is! I can dictate "open the notes app and create..." and the app opens before I even finish my sentence.