Raphael Friedmann

Understanding & using AI24 posts

New to this, or running AI for a team? Start at the top and read down.

From zeroFoundations · 17

What an LLM is, what a GPU does, and how to run one. No background needed.

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.

19 Mar 2026 5 min read

Why 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.

27 Mar 2026 5 min read

What 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.

3 Apr 2026 2 min read

How 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.

10 Apr 2026 2 min read

How 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.

17 Apr 2026 2 min read

Mixture of Experts: how a 30B model runs like a 3B one

The trick behind names like Qwen3-30B-A3B: split the model into many experts, run only a few per token. Why it suits a single GPU so well, and the headaches it brings.

12 May 2026 3 min read

How a model learns: training, in plain words

Every LLM starts as random noise and is shaped by one repeated loop: guess, measure the error, nudge billions of dials. Here's how that training actually works, and why it costs a fortune.

13 Jun 2026 4 min read

Pretraining, fine-tuning, and RLHF

A raw trained model can continue text but won't answer you. The three stages that turn a text-continuer into a helpful assistant, and which one you actually need.

14 Jun 2026 4 min read

AI that isn't an LLM

Language models get all the attention, but they're one corner of AI. A quick tour of the other big families, what each is for, and how to tell when an LLM is the wrong tool.

15 Jun 2026 4 min read

What 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.

16 Jun 2026 4 min read

How an agent uses tools and memory

The loop, one level down: how the model actually requests a tool, why its whole memory is just the growing transcript, and why long multi-step tasks fall apart.

17 Jun 2026 5 min read

Why 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, and not stupidity: it's because the model never sees letters at all. A plain-words tour of tokens.

18 Jun 2026 5 min read

Why 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, and one knob controls how loaded the dice are. Meet temperature.

19 Jun 2026 5 min read

Why models make things up

A model will hand you a wrong fact, a fake citation or an invented function with total confidence. It's not lying and it's not broken. Here's where 'hallucinations' actually come from, and how to work around them.

20 Jun 2026 6 min read

What the model remembers: the context window

An LLM has no memory between messages. Everything it 'knows' about your conversation is re-read from scratch each turn, and it only fits so much. Meet the context window, the single most useful thing to understand about how chatbots behave.

22 Jun 2026 5 min read

How 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 what happens to the image? A plain-words look at how vision gets bolted onto a model that only ever knew words.

23 Jun 2026 4 min read

How to actually ask: prompting without the magic words

There are no secret incantations. Good prompting is just clear instructions to a brilliant, literal-minded assistant with no memory. A practical guide that follows straight from how the model works.

23 Jun 2026 4 min read

Using AI for realOps & infra · 7

Twenty years of running infrastructure, pointed at using AI in practice. The honest version.

What an LLM can and can't do in your infrastructure

After twenty years of keeping systems running and a couple of years deep in LLMs, an honest split: where AI genuinely helps an ops team, and where it's a liability waiting to happen.

8 Jun 2026 5 min read

LLMs in the terminal: a sysadmin's honest list

The concrete, everyday ways an LLM actually earns its place in a sysadmin's workflow, and the handful of rules that keep it from causing real damage.

10 Jun 2026 4 min read

Self-hosting an LLM for your team: usually don't

The tempting case for running your own model, and the honest reason most teams shouldn't: a small model's error rate burns more working time than the API fees it saves. Plus the cases where it still wins.

12 Jun 2026 4 min read

When not to use AI: an ops take

The unfashionable half of the conversation. The cases where reaching for an LLM is the wrong choice, and a simple heuristic for telling them apart from the good ones.

14 Jun 2026 3 min read

When to let an agent loose: an ops take

An agent that can act can also act wrongly. After twenty years of running systems, here's how I decide how much rope to give one, and the guardrails that earn their keep.

17 Jun 2026 4 min read

Pointing an LLM at your own documents (RAG, honestly)

Everyone wants 'a ChatGPT that knows our internal docs'. The mechanism is called RAG, it's simpler than the hype, and most of the work is the boring retrieval half nobody demos. An ops-eye view.

21 Jun 2026 5 min read

Prompt injection: the security hole in every LLM app

The moment your AI reads anything an attacker can influence, a web page, an email, a document, that content can hijack it. There's no clean fix, only containment. The honest ops briefing on the vulnerability nobody demos.

24 Jun 2026 5 min read