Local AI for humans
ComfyUI's official AMD docs recommend using ROCm 7.2. However, I tested Comfy a month back with the then new ROCm 7.14 on an AMD Strix Halo (see my …
Most people building local AI focus on Nvidia, but AMD has great stuff too! Here are some people to follow:
DeepSeek's new harness only lets you run its web UI on 127.0.0.1 (localhost) by default — if you specify 0.0.0.0 as host, it'll throw an error and refuse …
Most discussion around open-weight AI models is around code and agentic capabilities, but how good are local LLMs at vision?
Like most AI nerds, I have a custom Telegram bot that runs on my PC. It's a vibe-coded harness inspired by OpenClaw / Hermes, but with a tiny, tiny subset …
Speculative decoding is an AI speedup technique where a small, fast "drafter" model guesses upcoming words. It speeds up text generation by letting the …
Musubi Tuner is a set of scripts for training LoRA (Low-Rank Adaptation) models with HunyuanVideo, Wan2.1/2.2, and many other image and video models.
ComfyUI's official AMD docs recommend using ROCm 7.2. However, I tested it with the latest ROCm 7.14 on an AMD Strix Halo, and it flies.
Krea 2 is a new, very capable open-weights image gen model. It runs on commodity hardware, super easy to use, and produces very good-looking results by …
This is my mini review of the ASUS ProArt 2026 GoPro Edition which I've owned for about a month now. This review is extremely opinionated, with some …