Part 1 Review
All ten days of Part 1 at a glance · short, with analogies · DAY 01–10
For ten days, you looked at what AI is, one day at a time. Here we pull all ten days into one place and run through them again.
No quizzes, no experiments. Just read it through. It's fine to pick only the days that feel fuzzy.
DAY 01 · Guessing the next word
Pick a piece, add it, pick again
AI doesn't make up a whole sentence at once. It picks just the next piece, adds it, then picks again. Repeat that pick hundreds of times, and you get the long answer we read. So AI isn't fetching an answer stored somewhere — it builds a new one every time.
DAY 02 · Tokens
That piece has a name: token
The piece AI picks has a name. It's called a token. A token isn't a letter or a word — common chunks stay whole, and unfamiliar ones get chopped up small. To you, 'What's for lunch today?' is four words. To an AI, it's about six tokens.
DAY 03 · Probability and temperature
The probability table and the temperature knob
To pick the next piece, AI scores every candidate, then holds a raffle where higher scores get more tickets. Temperature is the knob that sets how adventurous that raffle gets. Turn it down and #1 wins every time; turn it up and lower candidates pop up more often.
DAY 04 · Training
Training is tiny fixes, repeated
AI training isn't a sudden 'aha' — it's 'tiny fixes,' repeated. Hide part of a sentence, have it guess the next piece, then nudge the numbers inside by how much it missed. Repeat that an enormous number of times, and grammar and common sense soak into those numbers.
DAY 05 · Parameters
Parameters: how many numbers get tuned
How many numbers training tunes — that's the parameter count. The more there are, the bigger the container for patterns. Today's big models run from tens of billions to around 1 trillion — not a number you could ever count.
DAY 06 · Hallucination
Confidently making things up — hallucination
When AI calmly makes up facts that don't exist, it's called hallucination. It isn't trying to lie. It comes naturally with a setup that picks a plausible next piece. AI has no separate built-in way to flag 'I don't know this.'
DAY 07 · Memory limits
Not remembering — rereading
AI doesn't save your chat. Every time, it rereads the whole conversation so far, then answers. There's a limit to how much it can read at once. That limit is called the context length. As the chat gets longer, the early part gets pushed out of the window.
DAY 08 · Prompts
New question, new probability table
A prompt is the whole input you hand to AI. Change the words, and the probability table for the next piece changes too — so the answer changes a lot. You're not changing the AI — you're changing the question.
DAY 09 · Big models, small models
Size means parameter count
A 'big' model just means it has lots of parameters — the ones from DAY 05. Big models know a lot and can handle hard problems, but they're slow, pricey and only run on servers. Small models fit on your own device, so they're fast and work even without internet.
DAY 10 · Open and closed models
Where the core lives
A closed model's core stays on the company's servers. We can only talk to it through the front desk. With an open model, you can download that core — the weights — in full and run it on your own computer. You ask questions the same way — the difference is where the model lives.
Ten days, tied into one line
AI is a machine that picks the next piece. That piece is a token, the way it picks is probability, and what made those probabilities is training.
Hallucination, memory limits, and the differences in size and openness all follow from that. They weren't separate topics — it was one story, connected in a single line.
In Part 2, we trace where this thing came from, all the way back to the neuron that learned on its own, in 1958.
Learn more
- Attention Is All You Need (2017) — the Transformerarxiv.org/abs/1706.03762
- Neural Machine Translation of Rare Words with Subword Units (2015) — the BPE tokenizerarxiv.org/abs/1508.07909
- Learning representations by back-propagating errors (1986) — backpropagationnature.com/articles/323533a0
- Language Models are Few-Shot Learners (2020) — GPT-3, 175 billion parametersarxiv.org/abs/2005.14165
- Training Compute-Optimal Large Language Models (2022) — Chinchillaarxiv.org/abs/2203.15556
- A Survey on Hallucination in Large Language Models (2023)arxiv.org/abs/2311.05232
- Lost in the Middle (2023) — the middle of a long input gets used lessarxiv.org/abs/2307.03172
- Pre-train, Prompt, and Predict (2021) — a survey of promptingarxiv.org/abs/2107.13586
- Distilling the Knowledge in a Neural Network (2015) — distillationarxiv.org/abs/1503.02531
- Llama 2 release (2023) — open weights and the license debateen.wikipedia.org/wiki/Llama_(language_model)
- Mistral 7B (2023) — Apache 2.0mistral.ai/news/announcing-mistral-7b