All Series

Install Homebrew

The one-line Homebrew installer for macOS, Linux, and WSL, plus the PATH step Apple Silicon needs and a quick way to check it actually took.

Install Git

Install Git on macOS, Linux, and Windows, set your name and email so commits get attributed to you, and confirm it all worked in one command.

Install Node.js and npm without future regret

Install Node and npm through a version manager so you can switch versions per project. fnm is my pick, with nvm and Volta as alternatives.

Install Python the right way, with uv

Leave system Python alone. Install uv, then let it handle Python versions and per-project virtual envs from one fast binary.

AI, in plain words

What "AI" actually means, where the term came from, and why every product calls itself AI now. Sets up where machine learning and deep learning fit underneath.

Inside AI: machine learning and deep learning

Open the AI umbrella. Machine learning is the part that learns from data. Deep learning is ML done with neural networks, and that's where today's models live.

What makes a model: data and algorithm

A model is a file of learned numbers, produced by running an algorithm over data. Both ingredients matter, but bad data beats a good algorithm every time.

How a model learns: training and inference

Training is the expensive one-time event where a model's numbers get tuned. Inference is the cheap repeated use afterwards. The gap in cost is enormous, and it shapes the whole industry.

Where AI actually runs: cloud, local, edge

When you use AI, a model file is sitting on a real machine. There are only three places it can be, and which one decides almost everything else.

The major LLMs in 2026

A field guide to the closed frontier models and the open weights you can actually run. What the "B" numbers mean, and which size fits your machine.

What it takes to run a model on your own machine

Why VRAM is the one number that decides whether a local LLM runs, what quantization really does to a model file, and the hardware ladder from an 8GB laptop to a 192GB workstation.

Why Apple Silicon punches above its weight on local LLMs

Unified memory lets the GPU see all of RAM. Here's why that beats a discrete-GPU PC past 32B parameters, what fits in 16/32/64/128/192GB, and where Apple Silicon still loses.

The pitch for local LLMs in 2026

The case for running an LLM on the machine you already own. Privacy, no per-call cost, faster first token, no rate limits, and it works on a flight.

The local-LLM vocabulary

Parameters, B, dense vs MoE, base vs instruct, tokens, context windows, chat templates, GGUF, and quant suffixes. Read it once and any HuggingFace model card stops being scary.

Quantization, distillation, pruning: how a 140GB model fits on your laptop

Three ways to shrink an LLM, and why one of them does almost all the work. What Q4_K_M actually means and what each shortcut costs you.

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.

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.

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.

RAG done right: chunking and retrieval mechanics

Naive RAG breaks in practice long before the model does. Chunking strategy and embedding choice decide most of it, and here's where top-k search quietly fails.

Beyond vector search: hybrid, rerank, and graph RAG

When plain vector search hits its ceiling, three upgrades actually help: hybrid search, reranking, and graph RAG. When each one earns its added complexity.