Skip to content
JevDirectory.org
CommunityPractices & Patterns

Local Laya vs cloud Jev on Tetris

A video comparison of local Laya against cloud Jev on a Tetris agent, where the open-weights model made decisions 11 times faster on a 16 GB MacBook Air.

Open x.com
Category
Practices & Patterns
Format
Video
Published by
Community
Author
atomic.chat
Added
2026-09-25
Last verified
2026-09-25
Tagscommunityxvideoopen-modelsgames

Highlights

  • Reports an open-weights System One model beating cloud Jev on Tetris with 11 times faster decisions.
  • Ran locally on a 16 GB MacBook Air rather than a GPU host.
  • The Tetris harness itself was built with Grok 4.7, per the post.
  • Links to atomic.chat, an app for running models locally.

Watch out

A community comparison on a game task, not a controlled benchmark; speed depends on hardware and harness choices.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

Hacker News: Jev implemented in 25 lines of Python

bashbjorn400 points · 128 commentsJev in 25 Lines of PythonRead the thread on Hacker News

Hacker News: Kev: a tiny Jev-like family built on Qwen3.5

tosh458 points · 199 commentsKev: Tiny Jev-like family of decision models built on top of Qwen3.5Read the thread on Hacker News

X: Jev plus Astra beats the Ender Dragon for under a dollar

X: Jev plays Pokémon Showdown

More like this

What is Jev? (and is laya better?)
Scott Chacon runs hosted Jev against two local decision models, laya and kev, in a Tetris match and a GitHub Settings filter, with a public test repo.
Practices & PatternsVideo#community#video#open-models
Community
Shrinking gomoku from 225 moves to 40
A gomoku harness that does tactical work locally before asking Jev, shrinking 225 possible moves to about 40 candidates per turn.
Practices & PatternsPost#community#x#video
Community
JEVfire
67GitHub stars
An independent CUDA and vLLM take on parallel typed decisions: it scores verified single-token labels with the model's own head and assembles JSON in code.
Practices & Patterns#community#python#javascript
Communitykikoncuo/jevfireJavaScript
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

The open System One roundup

小墨同学
小墨同学
@xiaomovps
·

Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more

小墨同学
小墨同学
@xiaomovps

Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格

Image
Reply
Read 6 replies

Jev lands on the Vercel AI Gateway

Vercel ships the AI SDK provider for Jev

Computer use at 155× cheaper than Opus 5

aaron
aaron
vellum
@awlevin
·

i built computer use using @typesafeai ! it is 155x cheaper than opus 5, ~20x faster, and generalizes across OS's more on how it works in the vid & thread below:

Watch on X
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 69 replies

Foreman keeps coding agents on task

Unclutter: an ad and slop blocker that runs on Jev