All decision model projects

Social post about a public Jev-shaped API served by an open Qwen3.6-35B-A3B model so anyone can try typed decisions.

X post about a work-in-progress pull request reviewer that applies plain-English rules with Jev.

Japanese X thread summarising an analysis that inferred Jev's internals from about 10,000 API calls.

X post showing a jev() PostgreSQL function that filters rows by natural-language conditions with no index or embeddings.

Hacker News thread about Jeyzma, pitched as a Jev-style decision model run in the browser via Go, TinyGo and llama.cpp.

Social post describing a bot where Jev trades 15-minute and 1-hour BTC, ETH and SOL markets on Kalshi.

Chinese-language X post reading LangChain's Jev adoption as evidence that decision models fit fixed harness roles like routing.

TypeSafe founder's launch thread arguing that RLCD-trained decision models are a shorter path to economic value than chat models.

Chinese X post measuring Jev in a RAG pipeline over TypeSafe's docs: correct top-ranked answers rose from 7 to 17 of 20.

X post: a builder reports a small MLP on top of Qwen 4B already reproduces Jev-like decision behaviour.

X demo by Ephraim Duncan where Jev decides which model should serve a request before it is forwarded.

X demo of a CLI where you give a task and your subscription list, and Jev picks which model or agent should handle it.

X post listing nine jobs where a typed Jev decision can replace an expensive full LLM call.

X post contrasting a 706K-parameter model filling a form in one 50 ms pass with an LLM agent needing 23 turns and 39.6 s.

Hacker News thread where a builder claims prior open-sourced work on the same non-autoregressive decision architecture as Jev.

Hacker News thread on OpenAI answering TypeSafe's Jev with a decision API built on its Luna model.

X preview of fast browser automation using Jev with OpenCode's browser CLI.

X post claiming Playwright CLI with Jev choosing each step was 98% cheaper and twice as fast as the Playwright MCP.

X post arguing that purely engineering decisions in security work belong to Jev rather than to a chat model.

X post showing a Claude plugin that asks Jev to review redundant tool calls in about a second.

Japanese X post about running a Jev-style decision model locally, noting speed is still improvable.

Show HN thread for AT0M, a Jev-like System One decision model packaged as a single Rust binary.

Show HN thread for Decide, a tool for making Jev decisions from the shell, scripts and agent skills.

Show HN thread where Jev plays the Bletchley Park analyst for a software Bombe attacking Enigma ciphertext.

Show HN thread for jev-bisect, a pip package that finds answers with Jev by bisection search over options or ranges.

Show HN thread for Knowledge Signal, an open-source prototype that grades study notes against a rubric with Jev.

Show HN thread for onesie, a Unix-style pipeable CLI for using System One models like Jev in shell pipelines.

Show HN thread announcing an open-source decision model that its authors claim beats TypeSafe Jev.

X post in which a practitioner lists the six Jev uses he still expects to rely on after 60 days.

X post comparing Jev with a hand-built regex on 544 Spanish data-protection resolutions: 98.2% agreement for about five cents.