The Case Against Using LLMs for Programming: Learning Through Teaching and Simplification
By
ms7892
2mo ago· 1 min readenOpinion
38/100
Stale
Bagelometer↗
Yesterday's bagel, baked twice. Familiar and a bit tough.
Score38TypeopinionSentimentneutral
Summary
The article argues against using Large Language Models (LLMs) for programming, drawing on a Douglas Adams quote about teaching as the best way to truly understand something. The author suggests that explaining concepts to others, especially those who need simple explanations, forces deeper understanding. The core argument is that programming itself is about breaking down complex ideas into simple steps that even machines can understand, and this process of simplification is where real learning occurs. The author implies that relying on LLMs bypasses this essential learning process.
Key quotes
· 4 pulledWhat I mean is that if you really want to understand something, the best way is to try and explain it to someone else.
And the more slow and dim-witted your pupil, the more you have to break things down into more and more simple ideas.
By the time you've sorted out a complicated idea into little steps that even a stupid machine can deal with, you've certainly learned something about it yourself.
The teacher usually learns more than the pupil.
I originally posted this on Mastodon, but I thought I’d add it here too: “What I mean is that if you really want to understand something, the best way is to try and explain it to someone else…
