Understanding & using AI27 posts
A course, not an archive: numbered in reading order, start at 01. Every post stands alone if you already know the piece before it.
From zeroFoundations, 19 posts
What an LLM is, what a GPU does, and how to run one. No background needed.
01
What is an LLM, and how does it actually make words?
A jargon-free explanation of large language models: what they are, why they're basically a very good autocomplete, and how they write one word at a time.Start here02Why run AI on your own machine?
Cloud chatbots are easy and, honestly, hard to beat. The real and narrower case for running a model yourself, and the big things you give up to do it.03What a GPU is, and why AI needs one
Why running AI means buying a graphics card, what makes a GPU different from a CPU, and why the amount of memory on the card is the number that really matters.04How a 30-billion-parameter model fits on one card
Quantisation, explained for normal people: how shrinking each number in a model lets a giant fit on a desktop graphics card, and what it costs.05How to read a model's name and specs
Model names like Qwen3-30B-A3B-Q4_K_M look like a cat walked across the keyboard. Here's how to decode them, and the handful of specs that actually matter.06Mixture of Experts: how a 30B model runs like a 3B one
The trick behind Qwen3-30B-A3B: split the model into many experts, run only a few per token. Why it suits one GPU so well, and the headaches it brings.07How a model learns: training, in plain words
Every LLM starts as random noise, shaped by one loop: guess, measure the error, nudge billions of dials. How training works, and why it costs a fortune.08Pretraining, fine-tuning, and RLHF
A raw trained model can continue text but won't answer you. The three stages that turn it into a helpful assistant, and which one you actually need.09How a small model learns from a big one
Many of the small open models you can run at home were taught by a bigger model, not just by the internet. What distillation is, why it works so well, and what it can't hand down.10AI that isn't an LLM
Language models get all the attention, but they're one corner of AI. A tour of the other big families, what each is for, and when an LLM is the wrong tool.11What an AI agent actually is
Strip the buzzword and an agent is one simple thing: a language model put in a loop and handed tools, so it can do things instead of just talking about them.12How an agent uses tools and memory
The loop, one level down: how the model requests a tool, why its whole memory is just the growing transcript, and why long multi-step tasks fall apart.13Why an LLM trips over the r's in 'strawberry'
Ask a top model to count the letters in a word and it often gets it wrong. Not a bug, not stupidity: the model never sees letters at all. A tour of tokens.14Why you get a different answer every time
Ask a model the same thing twice and you can get two different replies. That's a deliberate dice-roll, not a glitch; one knob sets how loaded the dice are.15Why models make things up
A model hands you a wrong fact, a fake citation or an invented function with total confidence. Where 'hallucinations' come from, and how to work around them.16What the model remembers: the context window
An LLM has no memory between messages: it re-reads your whole conversation every turn, and only so much fits. Meet the context window.17How a model sees a picture
You can hand a modern AI a photo and ask about it. But a language model only understands tokens, so how is vision bolted onto a model that only knew words?18Why a model thinks before it answers
Modern models write pages of working-out before answering. That 'thinking' is computation bought with tokens: what it buys, what it costs, when it's wasted.19How to actually ask: prompting without the magic words
No secret incantations. Good prompting is just clear instructions to a brilliant, literal-minded assistant with no memory, straight from how the model works.Using AI for realOps & infra, 8 posts
Twenty years of running infrastructure, pointed at using AI in practice. The honest version.
20