Skip to content

Jeyzma is TypeSafeAI minus $850M plus Go/TinyGo/llama.cpp in the browser

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

Discussiondiscussion

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

This is a Hacker News discussion titled 'Jeyzma is TypeSafeAI minus $850M plus Go/TinyGo/llama.cpp in the browser'. From the title, it presents Jeyzma as a do-it-yourself, browser-local alternative to TypeSafe's hosted decision model, built with Go, TinyGo and llama.cpp.

No summary or README was available, so the project's design, claims and the discussion's content are not confirmed here.

What the decision model decides

TypeQuestionAnswers
OtherCan Jev-style typed decisions run locally in the browser? (discussion topic)(inferred)—

How it works

  1. Read the Hacker News thread
  2. Follow links to the Jeyzma project for details

Strengths

  • Points to a browser-local approach to decision models

Caveats

  • No summary or README available
  • Discussion thread, not a project page

At a glance

Type
Discussion
Status
discussion
Language
Go
Runtime
browser (TinyGo, llama.cpp)

Use cases and integrations

Frequently asked questions

What is Jeyzma?

Per the thread title, a browser-local take on TypeSafe-style decisions using Go, TinyGo and llama.cpp.

Where is the discussion?

On Hacker News, item 50031093.

Is the code available?

Not confirmed here; check links in the thread.

Related projects

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

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

    DiscussiondiscussionRust
  • Auto-updated bilingual leaderboard of Jev ecosystem projects, tutorials and discussions, discovered daily and sorted by GitHub stars.

    Projectproduction
  • ChatGPT-style web chat where every word of every reply is a Jev multiple-choice decision over a ~1,800-word vocabulary plus END.

    ProjectprototypeTypeScript
  • Experiment that deliberately misuses Jev as a text generator by asking which symbol comes next and sampling from the returned distribution.

    ProjectresearchPython
  • Chat client that makes Jev write by asking Next word? over a 20,000-word dictionary in 255-word buckets plus a run-off.

    ProjectresearchPython