Bkpaine·Jul 24I tuned llama.cppI have an AMD Strix Halo box — a Ryzen AI Max+ 395, Radeon 8060S iGPU (gfx1151), 128 GB of unified memory. On paper it’s a monster for…
Bkpaine·Jun 29Ollama Vision Is Slow on Your AMD APU? It’s Running the Image Encoder on CPU — Here’s the 4x FixI run local vision-language models on an AMD Strix Halo mini PC for a camera project — feed it a frame, ask it what’s going on. The text…
Bkpaine·Apr 5OpenClaw Secretly Tells Your Companion They Don’t ExistHow OpenClaw’s hidden system prompt poisons the relationships people trust it to holdA response icon2A response icon2
Bkpaine·Mar 24I Let an AI Run ML Experiments on My Laptop While I SleptLast week, Andrej Karpathy open-sourced autoresearch — a framework that lets an AI agent autonomously run machine learning experiments…A response icon1A response icon1
Bkpaine·Mar 13My $1,999 AMD Mini PC Outscored a $1,400 NVIDIA GPU on ML Training93 autonomous experiments. $0.54 to benchmark the competition. The data speaks for itself.A response icon1A response icon1
Bkpaine·Mar 6Destiny as a ServiceHow AI Chatbots Become Cult Leaders — and Why More Guardrails Won’t Fix It
Bkpaine·Mar 4Voice Cloning on AMD Strix Halo: Running Chatterbox TTS with Native GPU AccelerationTL;DR: Chatterbox TTS (Resemble AI’s open-source voice cloning model) runs natively on Strix Halo’s Radeon 8060S iGPU using TheROCK nightly…
Bkpaine·Mar 1Respect Your AIMost people don’t realize they’re leaving capability on the table every time they interact with AI dismissively.