Skip to content
Back to home
AI Games

Four kart racers from one prompt

Alexey Fateev ran one Mario Kart–style prompt four ways: DeepSeek and GPT-6 Astra alone, then each with the other as a subagent. Four builds, each from scratch.

last month

Alexey Fateev wanted a comparison, so he built the comparison four times. Same kart-racer prompt. DeepSeek with an Astra subagent, Astra with a DeepSeek subagent, then each model alone, because a pair of results was not enough.

Astra stayed on medium reasoning. DeepSeek stayed on max. Every version started from scratch. A Mario Kart–style game is a useful instrument here: a track, a camera and a lap are easy to see and hard to fake for ninety seconds.

The post is less about any one winner than about the spread. Four garages, one assignment, and a minute and a half of them driving.

Four kart racers from one prompt

Made with

Alexey Fateev

@superalesha

View the original post on X
I gave DeepSeek an Astra subagent. Then I gave Astra a DeepSeek subagent. Then I made both work alone, because apparently I needed 4 versions of Mario Kart. Same game prompt, each build from scratch. Astra on medium reasoning, DeepSeek on max throughout. I just wanted to see https://t.co/R7CUNbhu8Y

1.2K likes

likes
1,162
replies
115

Captured when this was curated, not live. —

Keep reading

Sac@Saccc_c

Sixteen days, and every planet is a place.

Sac spent 16 days with Claude Opus 5.5, Tripo and Blender turning each planet in The Little Prince into an explorable 3D scene. This is the original behind the five-hour remake already on this site.

AI GamesClaude Opus 5.5TripoBlender
1.4K16.6K