Tag: llm

All the articles with the tag "llm".

• MEMORY.md Is a Budget, Not a Document

  2 Nov, 2026

  Why MEMORY.md is a budget of prompt space rather than a document: the four harnesses, what each caps, who enforces it, and when not to build one at all.

• Choosing a Model for OpenCode via OpenRouter: Privacy, Price, and Performance

  26 Sep, 2026

  Picking a model and provider for OpenCode via OpenRouter — separating model origin from serving jurisdiction, tiering data-privacy risk, comparing DeepSeek/Qwen/GLM/Kimi/Gemini/OpenAI prices, and reproducing live rates with curl and Python.

• Why I Switched from Ollama to llama.cpp — and What I Learned

  3 Aug, 2026

  Switching a local LLM from Ollama to llama.cpp on a two-GPU Arch Linux GPD handheld — VRAM budget math, -ngl offloading, tuning, and a two-week verdict

• Build Your Own AI-Powered Wiki with Obsidian + Karpathy LLM Wiki + Ollama

  Updated: 21 Jul, 2026

  Build Obsidian + Karpathy LLM Wiki + Ollama