A plain-language explainer, part three
The first two parts showed you what our tiny AI looks like once it already knows how to guess text. This part shows where that ability actually came from — and it's a much duller story than "learning" makes it sound.
Every one of the AI's 10,788,929 internal numbers starts out random — no pattern, no letters, nothing copied from Shakespeare. Ask it to guess the next letter and it's no better than picking blind out of 65 letters.
There's no separate "teaching" step, no explanations, no rules written down anywhere. Just one loop, repeated over and over:
We ran this loop 5,000 times. Nobody ever told it what a "word" is, or what a "sentence" is, or gave it a grammar rule. Every nudge came from one thing only: was this specific guess a little less wrong than before?
Here's how wrong the AI actually was, checked every so often during those 5,000 loops. Shorter bar means less wrong:
It drops fast at first, then more slowly — each loop teaches it a little less than the one before, the same way the first hour of practicing anything teaches you more than the hundredth.
No — and now you can see exactly why. Every nudge in that loop was graded on one thing only: did the AI's final 65-letter guess get a little better? Nobody ever checked, or cared, what any single one of the 384 numbers in between was doing to help. As long as the final guess improved, the nudge stuck, whatever it did to those numbers.
That's the whole reason no dictionary exists for them. It's not that one was written and then lost. Training was never asked to produce one — only to make the final answer better, 5,000 times in a row. It succeeded at exactly that, and nothing more.