Learn AI visually.
One concept at a time, explained with simple diagrams and plain words. Written while I grow from AI support engineer to AI engineer.
Notes · methods, models and tools, with the claims checked · See all
- Notes
The AI keeps fixing the same bug: how to debug with AI tools
Why AI fixes go in circles, and a five-step way to find the real cause: reproduce, read, narrow down, change one thing, check.
- Notes
Is Bluehost's all-in-one AI plan worth it?
One subscription for ChatGPT, Claude, Gemini and Grok sounds like a bargain. I did the maths for India, and here is who it suits and who should skip it.
Explainers · 19 concepts · See the path · AI map
- Explainers
What are evals?
Tests for AI: a fixed set of questions with known good answers, run every time something changes.
- Explainers
What is prompt injection?
When text the AI reads, from a user or a document, sneaks in instructions that override the app's own.
- Explainers
What is tool calling?
How a model asks your app to run a function, such as checking an order, and then answers with the result.
- Explainers
What are guardrails?
The checks around an AI model that stop bad requests going in and bad answers coming out.
- Explainers
What is a harness?
The code wrapped around an AI model that turns it from something that writes text into something that can do work.
- Explainers
What is semantic caching?
How an AI product can skip the model and reuse an earlier answer when a new question means the same thing.
- Explainers
How does a neural network work?
Follow one email through a neural network, step by step: how it turns into numbers, gets a spam score, and how the network learns from its mistakes.
- Explainers
What are embeddings?
How computers turn meaning into numbers, so they can tell that 'refund' and 'money back' mean the same thing.
- Explainers
What are parameters?
What the B in '8B' or '70B' means, and why a bigger number isn't always a better model.
- Explainers
What is a context window?
Why long AI chats forget what you said at the start, what a context window is, and three habits that help.
- Explainers
What is a prompt?
Everything you type to an AI is a prompt. Here's how a few small changes get much better answers.
- Explainers
What is a token?
AI models don't read words. They read tokens. Here's what that means, and why it changes how you use them.
- Explainers
What is an AI agent?
The difference between an AI that talks and an AI that gets things done.
- Explainers
What is an AI hallucination?
Why AI sometimes makes things up with total confidence, and how to protect yourself.
- Explainers
What is an LLM?
The technology behind ChatGPT, Claude and Gemini, explained without the jargon.
- Explainers
What is fine-tuning?
Teaching an existing AI model your style or task with extra training, and when you shouldn't bother.
- Explainers
What is MCP?
The 'USB-C for AI': one standard way to plug AI apps into tools and data.
- Explainers
What is RAG?
How AI can answer questions about your own documents, and be more accurate, without being retrained.
- Explainers
What is temperature in AI?
The setting that decides whether an AI plays it safe or gets creative.
Papers · famous AI papers in plain words · See all
- Papers
Attention Is All You Need, in eight pictures
The 2017 paper behind today's AI chat models, shown as eight short animations you can watch and poke.
- Papers
BERT, in five pictures
The 2018 paper that taught a model language by hiding words and making it guess them, shown as five short animations.
- Papers
Chain-of-Thought, in five pictures
The 2022 paper that showed models answer better when the examples show their working, in five short animations.