Kimi K3 3D Scene Demo
MaziyarPanahi · x · 2026-07-19
The author had a model directly code a 3D arena within the browser, and then used a blind vision model to score the result.
This task was assigned to Kimi K3. Despite the fact that the "weights haven't even been released yet," the model generated a complete output without any manual modifications. The post primarily showcases this 3D generation/coding capability and asks the audience to vote for their preferred version.
Related event: Developers Build 3D Browser Games Cheaply Using Kimi K3(4 posts)→
More from Models
- Claim says Kimi was distilled from Fable, sparking a model-attribution jab — cephaloform · 2026-07-22
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22
- OpenAI’s Codex + GPT-5.6 Sol hits 99% recall in Project APE verification tests — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Macaron V1 adds LoRA RL on GLM 5.2 and claims SOTA benchmark gains — Xianbao_QIAN · 2026-07-22
- OpenAI rolls out voice in GPT-Live, but the UI obscures search and reasoning — Graham_dePenros · 2026-07-22