The knowledge hub
Every episode, supplement and Frontier Dispatch as a readable article — with the cinematic render, the full transcript, and the one idea that matters. 276 articles and counting.
01
Text becomes numbers
18 articles#8Ep2:30
Computers can't see letters.
Text is numbers all the way down — bytes, encodings, glyphs are stacked agreements, and the letter exists only at the final rendering step.
#9Ep2:30
Why 'é' is a trap.
Unicode gives é two legal spellings — identical glyphs, different bytes — so "looks identical" means nothing below the glyph layer…
#10Ep2:45
Models don't read words. They read tokens.
The token — a learned chunk from a fixed menu — is the atomic unit of AI: of pricing, context, speed, and failure.
#11Ep2:45
Why 'strawberry' breaks the AI.
Tokenization is why models miscount letters — they can't see inside a token.
#12Ep2:30
Why the AI thinks 9.11 > 9.9.
Two honest mechanisms collide: digit-chunk tokenization plus training-data neighborhoods where 9.11 genuinely "comes after" 9.9 (versions…
#13Ep2:30
One space can break your code.
Whitespace lives inside tokens — invisible characters change the token stream, so for a model, formatting IS content.
#14Ep2:30
The same sentence costs 3× more in Thai.
Tokenizers are trained mostly on English, so other languages pay more tokens per thought — in money, latency, and context space.
#15Ep3:00
Build a tokenizer from scratch (toy version).
Byte-Pair Encoding: start with characters, merge the most common adjacent pair, repeat — that's how every token is born.
#16Ep2:30
The merge rules ARE the tokenizer.
A tokenizer is a frozen ranked list of merges plus a numbered vocabulary — deterministic replay, zero intelligence, and the most permanent…
#17Ep2:30
What happens to a word it's never seen.
Byte-fallback guarantees any string can be tokenized — nothing is unrepresentable, some things are just expensive.
#18Ep2:15
Every token has a secret ID number.
The vocabulary maps each token to an integer — the model's real input is a list of numbers, and the numbers themselves are arbitrary.
#19Ep2:30
The haunted tokens.
Glitch tokens are menu slots whose table rows never got trained — feeding one in injects noise from nowhere, and the model breaks.
#20Ep2:30
The secret control characters of chat.
Special tokens — begin/end markers, role labels — are invisible punctuation the model obeys; "the assistant" is a formatting convention…
#21Ep2:45
Turning a number into meaning.
The embedding table: each token ID looks up a long learned vector — a list of thousands of numbers that IS what enters the model.
#22Ep2:45
Meaning is a direction, not a definition.
Similar concepts point in similar directions — the training game itself organizes the map, and no definition is stored anywhere.
#23Ep2:30
king − man + woman = ?
Vector arithmetic captures relationships — the analogy equation actually computes, honestly caveated as approximate and at its best on…
#24Ep2:30
How 'distance' between words is measured.
Cosine similarity — closeness is the angle between arrows, not ruler distance; direction carries the meaning.
#25Ep2:15
Why bigger vectors hold more nuance.
Embedding dimension is capacity — more coordinates, more room for distinctions — priced in compute, with no human-readable meaning per…