I gave Jev 3,282 of my X posts across 100M views and asked it to find what actually works for growth. 4,252,330 tokens $0.1282 for the full 8m 34s run! Each post got 8 questions about the topic, hook, tone, whether it teaches something, etc. How-to posts got 150 median likes Show more
Primitives
Score level
One entry in a Score's ordered criteria list; levels are numbered by array position from 0 and judged independently.
- Category
- Primitives
- Also known as
- —
- Related terms
- 5
- Directory entries
- 2
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
Score levels are ordered descriptions, at least two and at most ten. The model sees the descriptions, not the numbers, and judges each level separately — so adding "worse than level 1" to a description adds no signal. Well-separated levels with concrete signals work best.
The answer's score is the probability-weighted position across levels, and the legend maps each level number back to its description for logging and review.
Tagsprimitivesdesign
Related terms
Definitions that connect to this one.
ScoreRate the state against 2 to 10 ordered levels; returns a probability-weighted position, per-level probabilities, and confidence.PrimitivesCriteriaThe possible answers for a question: a map of options for Choice, an ordered list of levels for Score, or true/false for Noul.PrimitivesScore legendThe Score answer field that maps each level number back to its description, so results stay readable after the fact.PrimitivesWeighted scoreThe Score answer computed as each level number times its probability, which is why a score can land between two levels.Answers & ConfidencePrimitive limitsThe hard caps to design around: 255 Choice options, 2 to 10 Score levels, and a 64k context covering state plus questions.Primitives
From the directory
Rate content against 2 to 10 ordered levels. Returns a probability-weighted score that can land between levels, per-level probabilities, and confidence, with the arithmetic left to code.
Practices & PatternsDocs#official#primitives#score
Official
Instructions, option descriptions, score levels, and noul criteria all accept JSON, so you can label question parts, pass schemas and taxonomies, and keep candidate paths alive.
Practices & PatternsDocs#official#primitives#architecture
Official
From the community
Posts from builders shipping with Jev right now.
3,282 posts, eight questions each
Jev repositories worth a look, in Japanese
やぁ！兄弟たち！ Jevに関するGitHubの実用性と発展性がありそうなリポジトリをまとめたよ！ やはり、高速判断を要するComputerUseや完全自動トレードなんかに対しての活用が多い印象だね！ Jevは公式のウェイトリストも1日ほどで承認されるけど、待たなくてもVercel AI GatewayからModel: Show more
Company invoices, classified for the books
Caso de uso de @typesafeai: Revisar todas las facturas de la empresa y clasificarlas contablemente en segundos 🫠
Real-time Clippy that wakes up when you struggle
I built real-time Clippy with Jev. It quietly watches how you use the product and only wakes up when it thinks you’re struggling. Hesitating? Confused? Stuck? Clippy knows. Even its reactions are controlled by Jev. 👀
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
One-click invoice finder
Jev is fun! One-click invoice finder for any website 🧾 - Automatically finds billing pages using @typesafeai's Jev - List/download all invoices with 1 click - Works with Stripe billing portals too - Remembers where invoices live for next time Should I open-source it?
A visual reference finder
I built a visual reference finder with Jev One single prompt → 100 images from Cosmos, NASA, and The Met my new rabbit hole for creative work 🌻 Show more
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x