

… we had autocomplete that worked better before LLMs came along. If you’re not using an LLM to generate more code then what the fuck is the point.


… we had autocomplete that worked better before LLMs came along. If you’re not using an LLM to generate more code then what the fuck is the point.


I gave one example. In fact that’s one of the least bad examples. If that was the only problem with LLMs it wouldn’t really be that bad. But the actual reality is so much worse. But I was arguing to the point that the person I replied to made, which was about development. The problems I have with AI are not fixable without literally every government on earth taking a stand, which just will not happen.


The overwhelming majority of software development occurs on a team. You understanding what you’ve asked an AI to do doesn’t mean jack when you need to make sure an entire team can understand it five years from now. And LLMs tend to write code that is incomprehensible to another person the next day.


Completely disagree. The difficult part of software development was never writing code OR speed of delivery. It was understanding requirements and problem solving. LLMs still can not do either of those things and there is no evidence they ever will be able to.
An example of how harmful LLMs actually are to development can succinctly be described with an issue I had a few weeks ago. I found an issue in an open source project, code was fine if a bit hard to understand. I came up with a PR to fix the problem.
In the time from me checking out the code to submitting the PR, a little less than 24 hours, the maintainer had completely rewritten the entire project with Claude. It was complete nonsense. Incredibly difficult to understand. Abstracting things that didn’t need abstracting. My PR was useless, because the entire project was new. The maintainer definitely didn’t understand the changes either. If a bug came up there’s no way AI would be able to solve it (the bug was still there even though the code was entirely new).
LLMs don’t understand the code. They just make things that look like they will work. And then a human has to maintain it (or keep paying billions of dollars for Claude to try to fix it).


Even the install instructions are written by AI. Good grief
I’m not sure how the person you responded to did it, but LTT has a whole video series on doing just that from what I remember.
Huh? External sound does not mean the object produces sound.