Harness: I made Jev control the player, has access to WASD, space, click, and mouse movements. Astra is the planner that sends instructions to Jev async. Learning: Each time the agent would fail, Astra would add skills as mjs files, that it can draw upon in different scenarios, Show more
CommunityPractices & Patterns
Jev vs Jev in Gomoku
A Japanese experiment that builds a rules-based gomoku harness and replays a full Jev-versus-Jev game log to measure real per-move latency.
- Category
- Practices & Patterns
- Format
- Article
- Published by
- Community
- Author
- mizchi
- Added
- 2026-09-25
- Last verified
- 2026-09-25
Highlights
- A 25-move game took 13,913 ms, about 500 ms per move against a 50 to 500 ms claim.
- Per-move input tokens grew from roughly 746 to 3,052 as the game progressed.
- Confidence rose late, reaching 0.9 at move 19 and 0.83 on the winning move.
- The author estimates 110 to 130 ms of network latency from US West Coast servers.
Watch out
Japanese-language, preliminary, and based on one game; the latency explanation is the author's estimate.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev plus Astra beats the Ender Dragon for under a dollar
X: Jev plays Pokémon Showdown
1/8 Saw Jev from @typesafeai on my feed, so I made it play Pokemon Showdown. Codex built the harness. It was damn fast. Its choices were a mixed bag. Full match, video 1/2. This is a saved replay with decision data, latency and added reading pauses.
X: Jev plays Puyo Puyo with real-time board questions
Jev にぷよぷよをさせてみた。 - 実行エンジンは github.com/puyoai/puyoai 。ゲームはリアルタイムで進行 - 盤面とそれぞれのポジションにおいたあとの結果を与え、①今どのフェーズか ②フェーズごとに、戦略からどの結果がベストか の1+3つの質問をして、選択肢を選ぶ 画像は Random Show more
X: Jev plays Smash Bros. against itself
jev is insane 🤯 here is jev playing smash bros against itself he is controlling all 4 different characters. and literally deciding whats the best move to play against itself all within a fraction of a second i used over 22 million tokens to play this match and it only cost Show more
More like this
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
Community
kikoncuo/jevfireJavaScript
kikoncuo/jevfireJavaScript6GitHub stars
A toy archipelago air-traffic demo where every in-flight judgment - divert or continue, declare an emergency, give way, and who lands first - is made live by Jev from each plane's local state in about 150 ms.
Practices & Patterns#community#html#demo
Community
lbotinelly/jev-little-airwaysHTML
lbotinelly/jev-little-airwaysHTMLA 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.
Practices & PatternsVideo#community#x#video
Community
From the community
Posts from builders shipping with Jev right now.
Jev plus Astra beats the Ender Dragon for under a dollar
Harness: I made Jev control the player, has access to WASD, space, click, and mouse movements. Astra is the planner that sends instructions to Jev async. Learning: Each time the agent would fail, Astra would add skills as mjs files, that it can draw upon in different scenarios, Show more
Tool calling as classify plus action, back to twelve-factor agents
jev is the best excuse you could possibly have to go re-read 12 factor agents. Tool calling itself can be decomposed into classify+action, if you learn to design ai programs as pipelines that switch breathlessly between classification, structuring data, deterministic code, AND Show more
@dillon_mulroy
i think jev is resonating with devs so well b/c it unlocks so many opportunities for composing ai into systems and products rather than ai _becoming_ the product/system really does feel like it was a missing primitive
Why Jev encodes a state and outputs distributions instead
Jev is one of the more interesting model launches I have seen recently because it asks a very simple question: Why are we using autoregressive LLMs as insanely expensive if statements inside software? The easiest way to think about it is: LLM: text -> generate tokens Show more
@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
How the agent stack moved in Jev's first three days
Jev just landed and the agent stack moved in three days. TypeSafe AI released Jev on September 15. It is built for the work agents actually do most of the time: choose the next tool, score a risk, decide whether to retry, or answer yes or no. Latency is under half a second. Show more
Jev plays Doom at ~10 calls/sec for ~$7/hour
We love how this doomo doomonstrates real-time intelligence and what can be doone with code + AI! ~10 calls/sec = ~$7/hour
Jev plays Super Mario Bros.
got @typesafeai’s new model Jev to play Super Mario Bros. fast inference + structured outputs makes it surprisingly good for real time use cases. I'm excited to see what can be done with these new models!