Last time, I wrote about having AI create tools for tasks rather than having AI perform the tasks every time.This time, I ...

Even an older workstation-class eGPU like the NVIDIA Quadro P2200 delivers dramatically faster local LLM inference than CPU-only systems, with token-generation rates up to 8x higher. Running LLMs ...

With the popularity of "vibe coding," you might wonder what coding is all about. Python is a popular language to get started with, but if you're on Windows, here's why you're better off learning ...

Long time no see!It has been a while since my last post, but I plan to continue writing articles about things that catch my ...

Windows ML adds experimental llama.cpp support for GGUF models, a local OpenAI-compatible API, ONNX text generation and new runtime tools.