←back to thread

Some things to expect in 2025

(lwn.net)
258 points signa11 | 1 comments | 16 Jan 25 22:55 UTC | HN request time: 0.575s | source
Show context
christina97 ◴[16 Jan 25 23:42 UTC] No.42732390[source]▶
> A major project will discover that it has merged a lot of AI-generated code, a fact that may become evident when it becomes clear that the alleged author does not actually understand what the code does.

Not to detract from this point, but I don’t think I understand what half the code I have written does if it’s been more than a month since I wrote it…

replies(6): >>42732523 #>>42733051 #>>42733163 #>>42733942 #>>42734578 #>>42734654 #
1. elcritch ◴[17 Jan 25 01:43 UTC] No.42733163[source]▶
Well LLM generated code doesn't often work for non-trivial code or cases that aren't re-hashed a million times like fizzbuzz.

So I find it almost always requires going through the code to understand it in order to find "oh the LLM's statistical pattern matching made up this bit here".

I've been using Claude lately and it's pretty great for translating code from other languages. But in a few bits it just randomly swapped to variables or plain forgot to do something, etc.