Show HN: AT0M – a Jev Like System One decision model in a single Rust binary
Show HN thread for AT0M, a Jev-like System One decision model packaged as a single Rust binary.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This is a Hacker News Show HN thread titled 'AT0M - a Jev Like System One decision model in a single Rust binary'. No list summary or thread text was fetched, so details beyond the title are unavailable.
From the title, AT0M aims to provide Jev-style typed decisions locally from one self-contained Rust executable, which would make deployment simple. Model size, accuracy, licence and repository location are not known here.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Jev-style typed decisions served from a single Rust binary(inferred) | — |
How it works
- Download the single binary
- Send state and typed questions
- Receive probabilities locally
Strengths
- Single-binary deployment, per the title
Caveats
- Only the thread title is available
- No details on model quality or licence
At a glance
- Type
- Discussion
- Status
- discussion
- Language
- Rust
- Runtime
- Single binary
Use cases and integrations
Frequently asked questions
What is AT0M?
Per the thread title, a Jev-like System One decision model in a single Rust binary.
Where is it discussed?
news.ycombinator.com/item?id=49907865.
Is it TypeSafe's Jev?
No; it is described as Jev-like.
Related projects
Hacker News thread about Jeyzma, pitched as a Jev-style decision model run in the browser via Go, TinyGo and llama.cpp.
DiscussiondiscussionGoJapanese X post about running a Jev-style decision model locally, noting speed is still improvable.
DiscussiondiscussionAuto-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