An early-access test of TypeSafe's Jev: calibrated judgments for half a cent

Open on Blog

More like this

• Article16 Sep 2026

  [AINews] Jev: a System One Model that only decides/classifies/routes/scores

  AI News daily roundup leading with the Jev launch, summarising RLCD and TypeSafe's 20-200x speed and 40-400x cost claims. Frames Jev as part of a broader move toward task-specialised models.

  Latent.Space (AI News)Open[AINews] Jev: a System One Model that only decides/classifies/routes/scores on latent.space

  ChoiceScoreNoulIntent and model routingSemantic reranking
• Article16 Sep 2026

  Jev means structured output is interesting again

  Argues Jev's speed comes mainly from constrained single-token generation and aggressive prefill, techniques reproducible with existing LLMs, rather than a new architecture. Still treats very fast structured output as a new primitive, while doubting Jev matches frontier models on raw intelligence.

  Sean GoedeckeOpenJev means structured output is interesting again on seangoedecke.com
• Article18 Sep 2026

  A deep dive into Jev, TypeSafe's System One model

  Developer article framing Jev as a smart if-statement: pass structured data plus predefined questions, get probabilities over defined options. Covers Noul, Choice and Score, JavaScript, Python and Vercel AI SDK usage, and limits including arithmetic, dates, prose and images.

  Flavio CopesOpenA deep dive into Jev, TypeSafe's System One model on flaviocopes.com

  ChoiceScoreNoulIntent and model routingStructured extraction+1
• Article18 Sep 2026

  Testing Jev on public and private data: classifier or filter?

  16,000 calls comparing Jev with gpt-5.4-mini and gpt-5.6-luna on four public datasets, then on a few thousand real pipeline decisions. Covers where it wins, where it breaks, and how to use it.

  Aman KumarOpenTesting Jev on public and private data: classifier or filter? on amankumar.ai

  ChoiceNoulConfidence-gated actions
• Article17 Sep 2026

  heise: AI model Jev to make machines decide faster

  German outlet heise reports on Jev's 70-500ms latency, $0.042 per million input tokens, and RLCD. Notes the model gives no linguistic explanation for its decisions, which raises transparency questions.

  Tomislav BezmalinovicOpenheise: AI model Jev to make machines decide faster on heise.de

  ChoiceSupport inbox triageConfidence-gated actions
• Article17 Sep 2026

  How to Use Jev: A practical guide to TypeSafe's System One model

  Practical guide covering setup, the three primitives (Choice up to 255 options, Score across 2-10 levels, Noul as a yes/no probability), and five patterns: speculative fan-out, confidence-gated routing, composite scoring, cascading to a larger model, and retrieval before judgment.

  Prosper Otemuyiwa (Valyu AI)OpenHow to Use Jev: A practical guide to TypeSafe's System One model on dev.to

  ChoiceScoreNoulIntent and model routingConfidence-gated actions+3