The wasteland is taking shape.
🧟 Broken buildings, dead trees, voxel hordes, and a switch between overhead and first-person views. We’ve got a cheat mode for experiments, too. What should we test next? Initial build was done by deepseek v4 flash then later used gpt-6 sol
THIS / THAT model 1.1 is already here.
Nearly 2x improvement on complex-decision test, ahead of Kimi, GLM & DeepSeek. Same 1.88B parameters. Same ~31ms. Build. Ship. Repeat. trained by FLock
7 weeks with one DGX Spark:Qwen3.8-27B from 7.88 to 58.5 tok/s, same weights
DeepSeek-V4.1-Flash (485B) running on a single box Running ai models partly on nvme 7 image model configs, 19 hours of runtimeEvery number is in the Atlas: And more, my
I compared Mimo-V2.6-Flash, Grok-4.7, and DeepSeek-V4.1-Flash.
Same prompt with the /design command from Command Code. Reviewed gameplay UX/UI and cost: - Mimo-V2.6-Flash: 9/10 · $0.005 · one-shot playable game with the cheapest price - DSV4.1-Flash: 9/10 · $0.0089 · one-shot
You have reached the end of the archive
All of deepseek