[GuB-42]

The advantage of traditional auto-complete over AI is that it will typically list everything that fits: all methods, all variables and constants in scope, etc... It can even fetch the documentation if available. It is great for learning because it tells you all your options without deciding for you.

AI autocomplete essentially searches stackoverflow for you and pastes the first answer without context, adjusting it to match your code. If you are learning, just do the stackoverflow search yourself, or prompt you favorite chatbot if you insist on using AI, so you can have at least some explanation about why it is done like this.

[zahlman]

What if you had an AI system that could order the exhaustive list according to its likelihood estimate?

[GuB-42]

I think it is a good idea, and that's actually how Japanese word processors have been working since the late 70s!

The way to input Japanese is to type the word phonetically using a regular qwerty keyboard. The computer then finds all writings that match and order them by likelihood.

Calling that "AI" may be a little much for 70s tech, but it is definitely machine learning, as the machine is able to match patterns and take previous choices into account.