Ashita Orbis//understanding ai7 protocols
interactive

Understanding AI in a Month

Thirty days, one idea a day, from nothing to following the argument.

A thirty-day course in what these systems actually are. Each day is a written article with its figures and its sources, an audio edition, and a printable copy. Days are published as they are made.

  1. Day 12026-09-1012 min listen8 figures

    The Model Is Not the Product

    In July a benchmark score nearly tripled without anything inside the model changing. The interesting question is not how the software was improved.

  2. Day 22026-09-1011 min listen5 figures

    How Text Becomes Tokens

    The best-known failure of large language models is that they cannot count the letters in a word, and the best-known explanation for it is that the word arrives broken into pieces.

  3. Day 32026-09-1012 min listen5 figures

    One Token at a Time

    What "predict the next token" actually means — and the half of the sentence that almost every popular account leaves out.

  4. Day 42026-09-0712 min listen4 figures

    How Words Affect Other Words

    The operation that lets a word at the end of a sentence change what a pronoun in the middle refers to is nine years old, was named after something it does not do, and is now a minority of the layers in the models whose internals can be read.

  5. Day 52026-09-1012 min listen6 figures

    How an Answer Unfolds

    A machine asked the same question a thousand times, with greedy decoding requested, returned eighty distinct completions. What decides which word comes next, and how much of the past the decision may consult, are two settings — and both are somebody's decision rather than a fact about the machine.

  6. Day 62026-09-1012 min listen7 figures

    What the Application Adds

    A trained model reads text and writes text. Everything a product appears to do besides that — searching, opening files, running commands, remembering a previous conversation — is ordinary software deciding what text to place in front of it and what to do with the text it returns. That division decides a great deal about what a system costs to run. It decides less than the industry's own marketing suggests about whether the system is right.

6 of 30 days published; 24 still to come. Each day is a written article with its own figures, an audio edition, and a printable copy.