Running a local Typesafe Jev
Japanese X post about running a Jev-style decision model locally, noting speed is still improvable.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This is a post on X written in Japanese. According to the directory summary, the author attempts to run a Jev-style decision model locally and notes that its speed still has room for improvement.
No post text was fetched, so the model, hardware and numbers are not available here. It belongs to the wider community effort to reproduce the System One interface with open models on local hardware.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Typed decisions served by a local Jev-style model(inferred) | — |
How it works
- Set up an open model locally
- Serve Jev-style typed questions
- Measure speed
Strengths
- Shows community interest in local decision models
Caveats
- Grounded only in a one-line summary
- No code or benchmarks available here
At a glance
- Type
- Discussion
- Status
- discussion
Use cases and integrations
How curated lists describe it
X (Japanese): attempt at running a Jev-style decision model locally, with speed noted as still improvable.
yibie/awesome-jev
Frequently asked questions
What is the post about?
Running a Jev-style decision model locally.
What was the result?
The summary says it worked but speed is still improvable.
What language is it in?
Japanese.
Related projects
Hacker News thread about Jeyzma, pitched as a Jev-style decision model run in the browser via Go, TinyGo and llama.cpp.
DiscussiondiscussionGoShow HN thread for AT0M, a Jev-like System One decision model packaged as a single Rust binary.
DiscussiondiscussionRustAuto-updated bilingual leaderboard of Jev ecosystem projects, tutorials and discussions, discovered daily and sorted by GitHub stars.
ProjectproductionChatGPT-style web chat where every word of every reply is a Jev multiple-choice decision over a ~1,800-word vocabulary plus END.
ProjectprototypeTypeScriptExperiment that deliberately misuses Jev as a text generator by asking which symbol comes next and sampling from the returned distribution.
ProjectresearchPythonChat client that makes Jev write by asking Next word? over a 20,000-word dictionary in 255-word buckets plus a run-off.
ProjectresearchPython