Games & real time

JevにFlappyBirdをやらせてる。 canvasから情報取ってきて判断させてる。 #Jev https://t.co/H2G8Du0TPc

I upgraded Jev’s Kitchen Chaos after V1. Biggest change: the 4 chefs no longer make decisions at the exact same moment. Requests are now staggered, so each chef can react independently. Then I reran Jev vs Claude Opus 4.8 vs GPT-5.6 Sol. Results: 🥇 Jev: 495 🥈 Claude Opus 4.8: 455 🥉 GPT-5.6 Sol: 450 Watch the run 👇

Been poking JEV (https://t.co/0CYgSpQWpG) in two modes. Games: 1) Shooting game, me vs JEV, same targets. JEV 14 hits, 0 misses, 100% accuracy. Me about 82%. Avg decision about 352ms. 2) Crate Gate (10 Deep Vault). Spatial puzzle with live judgments and confidence. Work: My research bot (Olvia) runs a lengthy government document application. JEV is the gate before each execute step: what next, eno

Got Jev AI playing Minecraft, and I genuinely didn’t expect it to move this fast. In ~80 seconds it chopped wood, crafted tools, mined cobblestone and got the stone pickaxe upgrade. It still made some very AI mistakes though, It mined cobblestone, used it to get itself back out, then later had to go down for more. Built the setup with Astra’s help. Really cool seeing this actually work.

@typesafeai JEV plays TETRIS. Not too bad but not like a world champion yet. For every new piece, I made it pick the best placement among all the possibilities given to it by a custom-built TETRIS version. And it made decisions in less than 400ms on average. And cost is insanely low. Quite impressive.

i made Jev (@typesafeai) play clash royale. Qwen 3.8 27B on @cerebras reads the battlefield, OpenCV reads cards + elixir, and Jev picks the card + placement. fresh account, starter deck. it won multiple games against REAL people. i'd be so annoyed https://t.co/wPhFh6bYNn

Can you beat JEV at pong? defend your wall, add some traps and see how fast JEV can react . Try to beat it here : https://t.co/S4P1jVuK3d Each decision consume my credits, so JEV won't work if i'm out of credits wondering how long that will last. Going to sleep now. https://t.co/s0Z4oNzCVH

I’ve been experimenting with Jev from @typesafeai , and wanted to see what happens when you give it a live chess game. So I built a system where a Chrome extension captures the board state and move history, sends it to a local backend, and feeds the data into Jev. Jev predicts the next move, and I manually play it on the board. No Stockfish. Just Jev making the decisions. Here’s a 1-minute look at

実際動いてる時のゲーム画面（これも4倍速） 日本だと400-500msでしかJevが反応しないので、500msを1ターンとし、それを100msで動いた時の感触を見れるようにしている https://t.co/bgDqGjS4cc

箱庭諸島をJevが操作するゲーム作った！ 1ターンが500msとかになっているので本家箱庭諸島では味わえないRTSみたいになっている🔥 遊んだあとは遊んだ結果をmp4で出力可能！是非遊んでみてね https://t.co/tfDVjJfpIw https://t.co/6daoHMDnIP

Jevで『逆フラッピーバード』を作ってみました！ 暴走したAI（Jev）のミサイルが都市に届く前に、ガードレールを動かして防衛するゲームです🛡️ Jevはかなり手ごわいので、出現するアイテムもうまく活用して人類を守ってください。 https://t.co/EfQSnODNXl

I made Jev play chess against me. How did I do it? Jev can't generate a move. It's a classification model, so it only picks from options you hand it. That turns out to be easy to work around. Any position has a fixed set of legal moves, so I generate all of them in code and let Jev choose one. Then I built a small app with a basic UI and played it. First I wanted a number, so I ran it against 600

@GitHubNext Would be interested to hear how it stacks up? See https://t.co/2c2k0er2NK where I benchmarked Jev vs other models. Context is I used this to use it for realtime decision making to visualise the impact Jev has for these types of use cases. It's fat and still pretty intelligent https://t.co/J1zj0KDfmA

@typesafeai Jev decisions ! An original, inspectable life-and-civilization simulation. HTML, JavaScript and an authoritative Node.js server. A bundled isometric renderer works without a CDN; optional Three.js shows the same world. This is not an EA product or a reproduction of proprietary Sims assets. New voluntary actions require valid Jev decisions. Rendering, navigation, physical consequences a

I hooked up TypeSafe’s JEV to Snake. Every move is a live model decision. https://t.co/UXEUOKvDaQ

I let Jev choose the direction of the fabric in a music shader. It's sampled twice every second, reads the song's spectral analysis, and decides the flow over 1296 individual cells. Safe Return by Rob Simonsen https://t.co/iPGXOYqyN5 https://t.co/bsvLaz65mb

jev + astra crushing candy crush. > python capture > opencv reads the board: 11ms > valid moves calculated: 0.1ms > jev chooses best move: ~242ms > python drags: 180ms full move: 433ms (without game animations but includes mouse drag). https://t.co/KzzLZc3NRB

What if a model answers in ~200 ms and costs less than a pixel? You can put it in weird places. I put it in three experiments: 🌦️ A shader that reacts to text. 🔎 A table that filters itself in natural language. 🏙️ A city with a thousand npcs that react to what happens. thxs jev! https://t.co/5pJ8wOV80h

Jev使ってトロッコ問題解かせてみた。 命がかかっているのに即決されるし、選択は再現性あって面白い 車掌がレールを切り替えているのは独自の世界観ですw https://t.co/hilVF7h3Us

My toddler wanted to tap on the keyboard. Made this quickly where Jev picks up the next object. Things from @thiingsco https://t.co/kGbzW2to66

Tried Jev from @typesafeai on AresSim environment. Overall the Rover's movements until first 50 steps was great. Had to tweak the rules abit to get it work. But it did a decent job (on par with Masked PPO I trained earlier). Making the State form more efficient would also make Jev work better,

話題の新AI「Jev」でオセロゲームをつくったぴょん 盤面のうち正しそうなマスをガイドしてくれます AI vs AI戦も実装 強いかどうかは不明ですが、一回のAPI呼び出しはわずか250msで応答と高速。API使用料も表示していますが驚くほど安い！ Web版のURLをリプに貼ります。挑戦してね https://t.co/jW8twW2wT8

Made a GeoGuessr where the only clue is emoji. @typesafeai Jev reads a random point on Earth and scores all 254 emoji in my catalogue. You drop a pin. You're scored on distance and on how many emoji your pin shares with the target — so wrong place but right vibe still scores. https://t.co/RYUfnlMK3y

I ran @LeanCodePl Marionette with @typesafeai Jev. One sentence: "win the game." A Flutter game it had never seen. 5 puzzles, rules only on screen. It read the code, flipped the right switches, tapped blue, red, green. 🤯 9.7 s. $0.0012. ⚡ No LLM involved. Marionette reads the widget tree and taps, Jev decides 🧵

Jevで遊んでたら一晩でここまで来た。 ・話した言葉 → Jevが144種類から「形」を選ぶ ・雰囲気から「質感」も選ぶ（悲しい→雨、興奮→炎、説明→タイル） ・確率が割れたら粒子も割合どおりに分裂 LLMだと遅くて無理なやつが、0.3秒で返ってくるから成立してる。 https://t.co/WPF0eU3Lbc #Jev #TypeSafe #ClaudeCode

I gave four Jev-style decision models the controls to Doom: Jev, Laya, finetuned ModernCE and Qwen3.5. A deterministic Python adapter turns ViZDoom's visible-object labels + HUD into text. Each model picks turn, move or fire. No extra Doom-specific training. Same starting seed, separately recorded games. Each model's actions change its view. The video shows action probabilities, kills and survival

Jev にアクションゲームをプレイしてもらった TypeSafe Agent Skill x Astra を使用 プロンプト: Jevを使って、このゲームのプレイヤーをリアルタイムに操作し、安定してゴールできる自動プレイ機能を実装して。Jevの状態表示UIを画面下部に配置して。変更後の敵配置で実際に複数回プレイして、クリアできるまで調整して。

Yesterday, GLiNER2.5 played doom. Rapid play looks coherent, but Jev has a secret sauce: decisions. So, I kept the embedder and trained a small decision head on the output. Now it's a homebrew decider model on embeddings. What homebrew decider model will you make this weekend? https://t.co/vOgOyu4Ye8

okay Jev is an INSANE unlock, I just gave Mario a multiverse. built "Mario Never Dies" with @typesafeai's Jev + microsandbox Jev picks every move and every time Mario dies, we fork the entire VM into 4 timelines and try again. whichever Mario survives becomes canon. it is like the others never happened.

Jev opens up so many possibilities for gaming 🤯 🏁 I built Wordshift - the first semantic typing racer game built with Jev from @typesafeai Slower than a jet, bigger than an elephant, faster than a cheetah. The bigger the difference, the farther your car moves. https://t.co/elObRrcVti

X algorithm post simulation hits 5M views. built using JEV. https://t.co/ub7Jcm4Q7w

got access and been using Jev as the director for my VJ software given he answers in under 500ms with judgments and confidence, he picks the scene, palette, effects and the mix, once a bar in real time cost? around 1$ per 2hr dj set https://t.co/KSndabU5RI

using Jev as a chess engine, I call it alpha-jev. pretty unimpressive lol https://t.co/FMP6oTOKyV