Skip to main content
David Loor
AboutServicesProjectsBlogContact
←Back to Blog

#llm

3 articles tagged llm.

Found 3 posts
Jun 8, 2026
13 min read

Local Gemma was too slow with AIdaemon until I fixed llama.cpp and the prompt size

I wanted AIdaemon on local Gemma 4 26B through llama.cpp, not Ollama. Generation ran at ~45 tok/s on an M4 Pro. Agent turns still felt stuck because prefill on 14k-token prompts took 8 to 9 seconds before the model wrote a single word.

AI & agents
Mar 15, 2026
5 min read

AI agent patterns I learned from building AIdaemon

Seven well-known AI agent patterns and how they actually work inside AIdaemon, a self-hosted AI agent daemon I've been building in Rust.

AI & agents
Dec 8, 2025
3 min read

Why AI chatbots speak Markdown

Ever wondered why ChatGPT, Claude, and other AI models format their responses with **bold text** and [links](url)? It's Markdown, and there's a good reason for it.

AI & agentsWeb development

Stay Updated

Get the latest posts and insights delivered to your inbox.

No spam. Unsubscribe at any time.

Archive
  • Local Gemma was too slow with AIdaemon until I fixed llama.cpp and the prompt size
  • AI agent patterns I learned from building AIdaemon
  • Why AI chatbots speak Markdown
David Loor

AI Engineer & Architect

AboutServicesProjectsBlogBookshelf

© 2026 David Loor. All rights reserved.

david@davidloor.com