Prompting as an engineering discipline
A prompt that runs a thousand times a day needs to be treated like code, not a note you typed once. Few-shot, chain-of-thought, and structured output, with the trade-offs.
Blog
Engineering
Posts on AI engineering, LLM systems, and software development.
From running models to building systems
Running a model and building with one are different skills. This post opens the AI Engineering series and lays out why the next nine posts exist.
Local Llms#13
Troubleshooting local LLMs (and how to keep up after this series)
The full catalog of local-LLM failures: OOM, slow tok/s, garbage output, instruction drift, bad RAG hits, tool-call hallucination. Plus where to follow the field once you're on your own.
Local Llms#12
Fine-tuning a model locally
When fine-tuning is actually the right call (it usually isn't) and how to pull off a LoRA run on a 16GB Mac, with a worked Llama 3.2 3B example.
Local Llms#11
Local agents and tool use
Function calling on open models in 2026. Which ones actually work, why local agents break when they break, and the scaffolding that keeps them upright.
Local Llms#10
Local RAG and embeddings
Build a working local RAG pipeline in about 30 lines using nomic-embed-text, Chroma, and Llama 3.2. And why running it on your own machine beats the cloud for personal notes.
Wiring a local LLM into the tools you already use
How to point VS Code (Continue, Cline), web chat UIs (Open WebUI, LibreChat, Page Assist), and your own code at a local model using the OpenAI-compatible API. Swap cloud for local without rewriting anything.
Your first local LLM, start to finish
Install Ollama, pull Llama 3.2 3B, chat with it, hit its API, and fix the five things that break on a first install. You finish with a working local LLM.
Every machine can run a local LLM (here's what fits)
A per-tier guide to running local LLMs in 2026, from 8GB integrated graphics to a 192GB Mac Studio. Specific models, specific speeds, specific configs.
System requirements by OS for local LLMs
What macOS, Linux, and Windows each need before you run a local LLM in 2026. Mac is the smoothest, Linux gives you the most knobs, and native Windows finally just works.
Picking a local model by task
The 2026 open leaders, sorted by what you actually want to do: coding, chat, the small-model crowd, structured output, vision, embeddings, and audio.
Streaming, throughput, and the KV cache
Why TTFT and tok/s are different numbers, why streaming feels faster than it is, and the KV cache that makes the 1000th token cost about the same as the first.