Kimi K3 Built the Game. I Still Had to Play It. · Josh C. Simmons

← Writing<br>The first build

I gave Kimi K3 one prompt and asked it to build a browser game. The assignment was a first-person 3D maintenance game inside a procedurally generated server facility. The player had to collect data cores, reach a freight elevator, and descend three floors. The stack was Three.js, vanilla JavaScript, and Vite.

Kimi produced a playable game in one shot. It was fun. It also had rough edges that mattered immediately: a drone could clip through my body, and hitting a knocked-out drone could wake it back up. The game looked like a finished demo until I tried to play it like a person.

The code is on GitHub, and you can play the game here.

Testing still belonged to me

That is where the useful part begins. I described the two failures, asked Kimi to fix them in parallel, restarted the development server, and tested the result. The collision bug was gone. The projectile bug was gone. The model did the repair work, but I had to see the failure, name it, and decide what correct behavior meant.

Why the prompt mattered

The prompt was deliberately difficult. I did not give Kimi a flat map and ask it to add a character. I asked for procedural levels with a different layout each time the random seed changed. That forced the model to keep the architecture, gameplay rules, rendering, physics, and progression in its head at the same time.

What Kimi K3 is good at

Kimi K3 is clearly built for long-horizon coding tasks with a clear outcome. Give it a large project and it will make a lot of decisions for you. Give it a small task and it may still respond like you asked for a department.

What the first result cannot tell you

The model's biggest strength is also the part that makes the marketing claims dangerous. A playable game is a real result. It is also the first result that can be judged by a human. The work moves into testing, correction, security, performance, and the boring decisions that decide whether anybody can live with the software.

The price of the experiment

The price was surprisingly low. I used Kimi Code on the $199 monthly plan. After the initial specification, the first game build, the bug fixes, and a few chat tests, I had used less than 1% of the monthly quota. By rough math, the project cost about $2 on that plan. Kimi's pricing page lists the plan and its shared quota structure.

The time was a different story. When I asked Kimi to generate 100 taunts and add them to the game, the task took slightly more than 15 minutes. That is long enough to get coffee and long enough to lose the context of the work when you come back. The servers were under heavy load, so I cannot treat that speed as a final verdict. I can say that quality stayed much more consistent than the waiting time.

The engineering underneath

Moonshot's technical argument is interesting too. Kimi K3 is built on Kimi Delta Attention and Attention Residuals. The company says the combination produces an approximate 2.5x improvement in overall scaling efficiency compared with Kimi K2. If that claim holds up, it is the kind of engineering improvement that changes what a model can do without requiring a miracle on the hardware side. I walked through the claim in the video, and Moonshot's technical write-up lays out the architecture.

Somebody still owns the failures

Here is the part every executive presentation leaves out. A model can produce a system quickly. Somebody still has to define the system, catch the drone walking through the player, test the fix, and decide whether the result is safe enough to ship. That person did not disappear. The job moved closer to judgment and ownership, and companies will try to pay less for both.

AI is real. The people selling the labor story are the part I distrust. Kimi K3 can do work that used to require a room full of setup, code, and patience. It can also hand you a system whose failure modes appear only after you start playing it.

The model earned my recommendation. It did not earn a free pass.

- Dr. J

Letter<br>A letter when there is something to say.<br>No schedule, no filler. Unsubscribe anytime. Read a past letter.<br>Subscribe