A browser agent that finds flights in seven seconds. A Claude session cut from a million tokens to 86,000 in one second. A WHERE clause that reads plain English. Vercel's safety reviewer. We are collecting what people built with Jev in its first days, and what they argued about, each in their own words. Nobody in these bylines is on eChai, and every entry links back to where it was posted.
9 entries Clear
Vipul Sharma's Minecraft agents ask Jev whether to fight or run, from what the agent can see, the mob count, its weapon and its health; one broke off mid-fight as the odds turned.
Vipul Sharma
2h
I hooked up Jev by @typesafeai to a few agents on my Minecraft world. Look at how Jev decides when they should fight and when they should run away.
Jev rates the odds from what the agent can see, mob count, weapon, how hurt it is, and runs away when they are bad. One broke off mid-fight as its odds turned.
Mahmoud's simulation of fifteen autonomous drones through an asteroid field, Jev deciding for each in under 300 ms, all fifteen arriving.
Mahmoud
2h
Jev can control a swarm of 15 autonomous drones in real time!
I built a simulation to test it navigating an asteroid field:
• Decision latency: < 300ms
• Survival rate: 100% (all 15 reached the destination)
Built with @typesafeai by @CompleteSkeptic
Hassan El Mghari's chess match: GLM 5.3 won in 29 moves, Jev played each move in about 0.3 seconds for under a hundredth of a cent against GLM's 5.8 seconds and 0.8 cents, and the whole game cost 24 cents. His takeaway is the hybrid pattern he had already used for fraud detection.
Hassan El Mghari
4h
Jev vs GLM 5.3 at chess!
Results:
◾ GLM 5.3 won by checkmate in 29 moves
◾ Jev: ~0.3s and <$0.0001 per move
◾ GLM 5.3: ~5.8s and ~$0.008 per move
◾ The whole game cost 24 cents
My main takeaway is that it's often useful to use each one to their strengths:
◾ Fast, well-defined classification → specialized models like Jev
◾ Classifications that need reasoning or lookahead → LLMs like GLM 5.3
◾ Real classification pipelines → hybrid. Jev handles the easy calls, an open model handles the hard ones.
The future is multi-model!
Mau Baron has Jev playing all four characters in a Smash Bros match against itself: 22 million tokens for the match, which he says cost a couple of cents.
Mau Baron
22h
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 me a couple of cents...
jev does not replace gpt6 astra
but the possibilities with its instant response time
are endless
Jarrod Watts again, with a 24/7 Twitch stream of Jev trying to beat Minecraft's Ender Dragon one decision at a time.
Jarrod Watts
1d
Introducing Jev Plays Minecraft!
A 24/7 livestream where Jev attempts to defeat the Ender Dragon, one decision at a time.
→
Max Blade's Subway Surfers run, fifty games at once. The film runs past three minutes, so it plays where it was posted.
Max Blade
1d
jev is insane 🤯
Here is Jev playing subway surfers at super human speed, and also playing 50 games at once.
cost less than a cent to do this run.
Jev does not replace llms like astra or fable, but opens up an entirely new world of capabilities.
Paul Wei, writing in Chinese. He had earlier used GPT-6 Astra to play Slay the Spire 2, which could play but slowly; on Jev each move takes 0.7 seconds, and he says the screen moved before he had read it.
Paul Wei
1d
昨天出的 https://typesafe.ai Jev 模型
适合高频决策，那岂不又是适合打游戏？
之前用 GPT-6 Astra 代打杀戮尖塔2
能力强但速度慢。
我刚实测用 Jev 打，行动思考只需 0.7秒，
画面我都没看清它就操作完了。
这超人类游戏速度，
着实又让我震惊瘫坐了😅
语言很难描述这感觉，看视频⬇️
Faadil Shaik, the day after launch, with the first game anyone outside TypeSafe put it on.
Faadil Shaik
2d
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!
The second post in the launch thread, and the demo the whole week kept coming back to: Jev reading Doom's game state as text and picking the next move about ten times a second, at what TypeSafe puts at roughly $7 an hour. The lab says the input is a structured text state rather than the screen.
Diogo Almeida
3d
We love how this doomo doomonstrates real-time intelligence and what can be doone with code + AI!
~10 calls/sec = ~$7/hour
