CCommunity contributorResources

Hacker News launch thread

1,800-point thread debating whether typed decisions replace LLM calls for classification, routing, and scoring.

Open resource

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement.

Keep exploring

Similar to Hacker News launch thread

Browse all

Launch thread by Diogo Almeida

Articles & threads
TypeSafe's founder on why RLCD-trained decision models are a shorter path to value than chat models.
CMade byCommunity contributor

Verdict (Open-jev) launch thread

Articles & threads
Hemant Kumar on his 151M ModernBERT reproduction: 0.83% adaptive calibration error, 3.0% of predictions flip when the option list is reversed, 35.6ms on CPU, with the failed use cases reported alongside the wins.
CMade byCommunity contributor

Early Jev tools roundup

Articles & threads
Thread cataloguing the first wave of Jev tools: MCP servers, routers, reviewers, and browser agents.
CMade byCommunity contributor

Patterns

Official
Speculative fan-out, confidence-gated routing, composite scoring, and intent routing.
TMade byTypeSafe AI

Introducing System One Models and Jev

Official
Launch post: architecture, RLCD training, pricing, Doom and Wikiracing demos, FAQ.
TMade byTypeSafe AI
awesome-jev-typesafe project preview

awesome-jev-typesafe

Other lists
Typed decisions with TypeSafe's Jev, the first System One model
VMade byvalentynkit132

Cookbooks

Official
Reproducible recipes: parallel questions, reranking, guardrails, citation checks, extraction, hierarchical classification.
TMade byTypeSafe AI
awesome-jev-tools project preview

awesome-jev-tools

Other lists
A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.
VMade byv-modal703
awesome-jev (yibie) project preview

awesome-jev (yibie)

Other lists
A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.
YMade byyibie1.6k