grep -l "#llms" posts/*
#llms
17 posts · all posts
- The agent loop, visually
- Mixture of experts, visually
- Local models are good now
- KV caches and why context is expensive
- Speculative decoding, visually
- How LLM tool calling actually works
- Picking a model per task
- GPT-5 and choosing models on evals, not launches
- The support bot that invented a policy
- DeepSeek-R1, and what a cheap open reasoning model changes
- The Model Context Protocol
- Computer use and the first real agents
- Reasoning models
- Is open-weights AI the path forward?
- An agent that files my expenses
- Retrieval-augmented generation, visually
- Llama 2 on my laptop