JEV Breakdown: The First AI Model Built For Code
Walks through the Choice, Score and Noul primitives live in the TypeSafe playground, with speed and cost numbers and their caveats.
Video
Videos about System One AI models and Jev
Recorded walkthroughs and explainers, including launch coverage in Japanese, Chinese, Korean and Portuguese. Most run under twenty minutes and cover the same ground: what a typed decision is, what it costs, and when you would reach for one instead of a chat model. View counts are whatever the platform reported on the day the entry was added.
26 videos
All entries
Showing 26 of 26
Jev Explained: Demos and Use Cases
CJ from Syntax explains what Jev is, how it works, and walks through several use cases and demos. 17 minutes.
Video
Jev: The Schema-Safe AI That Could Change Automation Forever
Technical breakdown of schema-constrained output, RLCD, the Doom and Wikiracing demos, and pricing. Lists limits including the 255-option cap on Choice and the absence of public benchmarks or released weights.
85k viewsLatency 70-500 msChoice cap 255 options
VideoReal-time control
Tetris Bench: Jev vs Laya-MLX
Video Tetris benchmark: Laya-MLX runs fast on a MacBook at about 84ms per decision but loses to Jev in all three rounds.
Tony Dinh (@tdinh_me)OpenTetris Bench: Jev vs Laya-MLX on x.com73k viewsLaya latency ~84 msResult Jev won 3/3
VideoReal-time control
This New Frontier Model Is Not An LLM.
Walks through the launch video, why decision models need to exist, and how they differ from LLMs in use. 15 minutes.
Video
Meet Jev: The AI Built to Make Decisions
Tests Jev on the creator's own inbox, classifying 100 then 1,000 emails by category, priority, spam and reply-needed at around 200ms average response time. Ends by checking the actual bill.
67k viewsAvg response time ~200 msSpeed claim tested ~200x
Jev (Fully Tested) + Browser Use: Fastest AI Agent I've Tried Yet
Runs Jev through support routing, refund detection, a prompt-injection attempt, exact-value selection, agent auditing and browser automation, with evaluation times as low as 92ms. Notes constrained outputs do not guarantee correct answers when the option list is incomplete.
Is Jev What AI Has Been Missing? I Tested It.
Hands-on test of Jev through the TypeSafe console with commentary on where it fits. 17 minutes.
Video
Local Laya vs Cloud Jev on the Same Snake Game
30-second Snake benchmark: a local 421M Laya checkpoint scores 46 at 86.5 decisions per second, while Jev 1.13.0 over the cloud API scores 1 at 3.2 decisions per second.
Simplifying AI (@simplifyinAI)OpenLocal Laya vs Cloud Jev on the Same Snake Game on x.com24k viewsLaya speed 86.5/sJev speed 3.2/s
VideoReal-time control
Jev AI Is INSANE... 193x Faster Than LLMs?!
Breaks down the side-by-side against GPT-5.6 Terra, the 193.6x faster and 444.6x cheaper workflow evals, and the 0% type-error chart. Covers the Doom and Wikiracing demos.
VideoReal-time control
System One Jev (Fully Explained): Does this really beat Transformer models?
Examines the speed and cost claims and what the published benchmarks show, noting Jev competes on some tasks and falls well behind on others. Clarifies the zero-hallucination claim covers output structure, not decision correctness.
AISeeKing17k viewsOpenSystem One Jev (Fully Explained): Does this really beat Transformer models? on youtube.comVideo
System 1 Models Jev Explained: 200ms AI Decisions, Zero Token Streaming
Explains the autoregressive latency floor set by memory bandwidth per token and how a single-pass architecture bypasses it. Covers the Kahneman framing, calibration and the Jevons Paradox naming.
Dots and Arrows15k viewsOpenSystem 1 Models Jev Explained: 200ms AI Decisions, Zero Token Streaming on youtube.comVideo
Jev: The Model That Killed ChatGPT's Core Idea? RLCD Explained
Short introduction to Jev focused on RLCD, Reinforcement Learning for Calibrated Decisions, as the training method behind the model.
Fahd Mirza15k viewsOpenJev: The Model That Killed ChatGPT's Core Idea? RLCD Explained on youtube.comVideo
Laya vs Jev Latency Demo
A maze demo comparing decision latency: local Laya on a base M5 responds at a 19ms median, versus roughly 300ms from Jev's cloud API for the same task.
VideoReal-time control
Livestream Coding with the new TypeSafe AI JEV Model
Livestream coding session against the Jev API, plus discussion of network architectures that could produce this kind of JSON predictor model.
Neural Breakdown with AVB13k viewsOpenLivestream Coding with the new TypeSafe AI JEV Model on youtube.comVideo
What Is Jev, the New Model From TypeSafe AI? (Tech Brew Ride Home)
Podcast segment covering the launch, the $40M raise, Almeida's path from RLHF to RLCD, and the 70-500ms response times. Explains the name as a nod to Jevons Paradox.
Tech Brew Ride Home Podcast (Brian McCullough)13k viewsOpenWhat Is Jev, the New Model From TypeSafe AI? (Tech Brew Ride Home) on youtube.comVideo
Jev, Laya-MLX and a Custom JAX Build on a Local Game Benchmark
Video benchmark where Jev wins outright as a cloud model, while a self-built JAX model ties with Laya-MLX among the local, on-device options.
Tom Siwik (@tomhacks)11k viewsOpenJev, Laya-MLX and a Custom JAX Build on a Local Game Benchmark on x.comVideoReal-time control
Mercury Decide vs Jev in chess
Video demo from Inception's Mercury Decide launch post, showing it playing Jev at chess. Inception claims up to 14 decisions per second and the top JevBench v1.4 spot on OpenRouter; neither was independently run.
Video
Home-Made Snake Benchmark: Jev vs Laya-MLX vs Kev-4B
Custom Snake benchmark comparing Jev over the API against locally run Laya-MLX and Kev-4B: Jev had zero deaths, Kev died twice at about 175ms latency, and Laya died early despite roughly 33ms latency.
Tobias Wupperfeld (@tobiaswup)3.1k viewsOpenHome-Made Snake Benchmark: Jev vs Laya-MLX vs Kev-4B on x.comVideoReal-time control
I tested Jev AI: Is it faster than Gemini?
Three real console calls with animated diagrams comparing Jev latency against Gemini.
Video
Laya Beats Jev 43-1 in Snake, Wifi Off
A video benchmark where local Laya beats API-hosted Jev 43-1 in Snake with wifi off: 86.4 decisions per second at 9.2ms P50 latency for Laya against 3.2 decisions per second at 308.7ms round trip for Jev, same schema and seed.
VideoReal-time control
Seven Open-Source Jev-Family Models Tested on JevBench
21-minute video scoring seven open-source Jev-family models on JevBench, ending with Laya, and noting write-ups conflate the multilingual 322M checkpoint's 1k context with the 421M English checkpoint's 512.
Video
Laya plays tic-tac-toe in Unity
Video of a Unity scene running Laya locally as a tic-tac-toe opponent, using receptron's ONNX export of the model through asus4's onnxruntime-unity plugin.
VideoReal-time control
Jev vs Laya: 1v1 Doom Deathmatch
A video of Jev and Laya fighting a 1v1 Doom deathmatch with monsters between them, first to five kills wins. Jev's calls were sharper and needed fewer corrections, but Laya decided twice as often and won 5 to 1.
VideoReal-time control
Pac-Man Wired to Laya-MLX
Video demo of Pac-Man controlled entirely by typed decisions from Laya-MLX running locally on Apple Silicon: 351 steps, a win, and 224 guardrail interventions logged.
VideoReal-time control
Jev plays Overcooked
Video demo of a harness for playing Overcooked: a planning model builds a live understanding of the level while Jev agents make decisions in real time.
VideoReal-time control
Nothing matches those filters
Clear a filter to widen the search, or send us the thing you were looking for.