What does it mean for AI to 'learn' something?
Training isn't a 'lightbulb moment' — it's 'fixing a little,' over and over.
1 · Think first
For AI, learning isn't understanding the way it is for people — it's a process of nudging numbers (weights) a little at a time so they get closer to the right answer.
The method is simple: hide part of a sentence, have it guess the next word, then tweak the weights slightly by however much it was off.
Do this on internet text and repeat it hundreds of billions of times, and you get a big bundle of numbers with grammar and common sense melted right in.
2 · Experiment · Put it in order
Try it — put the training cycle in order
Put the steps of 'learning by repeating' in order, for three situations.
Tap the pieces below in the order you think is right.
Figure
In one picture
Repeat four steps hundreds of billions of times, and random guesses slowly turn natural.
3 · Quiz
Quick check
Three questions. Pick an answer and it's marked right away, with the reason why.
Today in one line
Today in one line
Training isn't a 'lightbulb moment' —
it's 'fixing a little,' over and over.
Learn more
- By the way, this process (fixing the weights using the error) has a name — it's called backpropagation, and there's a 1986 paper that made the idea widely known — Learning representations by back-propagating errors