It's amazing how far open source LLMs have come.
Qwen3-32b recreated the Windows95 Starfield screensaver as a web app with the bonus feature to enable "warp drive" on click. This was generated with reasoning disabled (/no_think) using a 4-bit quant running locally on a 4090.
Here's the result: https://codepen.io/mekelef486/pen/xbbWGpX
Model: Qwen3-32B-Q4_K_M.gguf (Unsloth quant)
Llama.cpp Server Docker Config:
docker run \
-p 8080:8080 \
-v /path/to/models:/models \
--name llama-cpp-qwen3-32b \
--gpus all \
ghcr.io/ggerganov/llama.cpp:server-cuda \
-m /models/qwen3-32b-q4_k_m.gguf \
--host 0.0.0.0 --port 8080 \
--n-gpu-layers 65 \
--ctx-size 13000 \
--temp 0.7 \
--top-p 0.8 \
--top-k 20 \
--min-p 0
System Prompt:
You are a helpful expert and aid. Communicate clearly and succinctly. Avoid emojis.
User Prompt:
Create a simple web app that uses javascript to visualize a simple starfield, where the user is racing forward through the stars from a first person point of view like in the old Microsoft screensaver. Stars must be uniformly distributed. Clicking inside the window enables "warp speed" mode, where the visualization speeds up and star trails are added. The app must be fully contained in a single HTML file. /no_think
Not OP, but I'd be more interested in making a tiny ball round enough to roll across a surface and fall into a hole (not the "absence of an electron" meaning of that word). And I'd want it achieved through gravitational forces rather than electromagnetic. I feel like that makes the problem harder and largely makes it a materials science question. Someone in MEMS research probably has a good idea of how to approach this.
With those parameters, the system would probably need to operate in a high vacuum with as little interaction from electromagnetic forces as possible. All materials used should probably have a low permittivity to reduce the amount of static charge buildup from friction. Intuitively, I feel like it makes sense to use the same material for everything. But it might not be that simple. Maybe the material used to make the smallest round ball isn't well suited to making the smoothest surface for a short putting green?
I dunno, I'm just a guy who took a few classes on semiconductor design in undergrad spit balling.