Back to articles

Tag archive

#dgxspark

[Day 13] I got a cat to "talk." The biggest wall: the AI couldn't recognize the cat's face
Jul 3, 2026

[Day 13] I got a cat to "talk." The biggest wall: the AI couldn't recognize the cat's face

Day 13 of my 100-experiment local LLM challenge. I drove a single cat image with human facial motion to make a "talking cat" with LivePortrait, instead of putting my own face on camera. It worked — but the hard part wasn't the animation, it was getting the AI to recognize the cat's face. The fix was a no-compile patch for XPose. All local on a DGX Spark.

Jul 3, 20265 min read0 reactions0 comments
[Day 12] I tried to build a line-art LoRA from video frames, and the characters' heads fused together
Jun 23, 2026

[Day 12] I tried to build a line-art LoRA from video frames, and the characters' heads fused together

Day 12 of my 100-experiment local LLM challenge. I tried to build a line-art LoRA of my own hand-drawn animation by ripping frames out of the video, instead of preparing stills by hand. Single characters came out broken (fused heads, baked-in backgrounds), I fixed most of it by rebuilding the dataset — but "two characters together" was impossible from video, and the only real fix is to hand-draw the stills. All local on a DGX Spark.

Jun 23, 20266 min read0 reactions0 comments
[Day 15] A cat photo became a video — with a meow. Two local video AIs compared: 30s vs 475s
Jul 13, 2026

[Day 15] A cat photo became a video — with a meow. Two local video AIs compared: 30s vs 475s

Day 15 of my 100-experiment local LLM challenge. I turned one photo of my family cat into a short video with two local video AIs on a DGX Spark: LTX-2.3 generated a 4s video WITH a meow sound in 30 seconds; Wan 2.2 took 475 seconds for near-photoreal quality but no audio. Plus a first/last-frame trick that let me design a camera zoom.

Jul 13, 20265 min read1 reactions0 comments
[Day 14] I quizzed an AI on cat meows. It scored worse than random guessing
Jul 9, 2026

[Day 14] I quizzed an AI on cat meows. It scored worse than random guessing

Day 14 of my 100-experiment local LLM challenge. I asked a general-purpose audio LLM (Qwen2-Audio) to guess what a cat wants from its meow, using a labeled research dataset of 440 meows. It scored 23.3% on a 3-choice quiz — below random — and a shuffled-options control revealed it wasn't really listening at all. Meanwhile Whisper transcribed the meows as "Thank you for watching!" All local on a DGX Spark.

Jul 9, 20265 min read0 reactions0 comments