Local AI
Ollama Not Using GPU? Checklist for NVIDIA, AMD, Docker
Short answer: run ollama ps and read the PROCESSOR column. 100% GPU is what you want. 100% CPU means Ollama found no usable GPU; a s...
Archive
DevOpsCompass
Linux
sudo-rs on Ubuntu 26.04: What Breaks and How to Switch Back
Short answer: Ubuntu 26.04 LTS uses sudo-rs (a Rust rewrite of sudo, version 0.2.13 in our test) as the default sudo . Your /etc/sudoer...
Local AI
Ollama API Guide: curl, Python, OpenAI Endpoint, Embeddings
Short answer: the Ollama server listens on http://localhost:11434 . Native endpoints live under /api ( /api/chat , /api/generate , /api...
AI News
Why Claude Switched Models: Opus 5.5 Fallback Explained
In short: Anthropic's classifiers read every request to Opus 5.5 (and Opus 5 and Fable 5/5.1), including files and web results Clau...