Re:Two things LLM coding agents are still bad at
by mr_mitm on Thursday October 09, 2025 @06:54AM
(#45525930)
A meticulous coder probably wouldn't have typed out 40 URLs just because they want to move them from one file to another. They would copy-past them and run some sed-like commands. You could instruct an LLM agent to do something similar. For modifying a lot of files or a lot of lines, I instruct them to write a script that does what I need instead of telling them to do it themselves.
Re:Two things LLM coding agents are still bad at
by thunky on Thursday October 09, 2025 @08:35AM
(#45526750)
> I have already had to correct a LOT of crap similar to the above in refactoring-done-via-LLM over the last year
The person using the LLM should be reviewing their code before submitting it to you for review. If you can catch a copy paste error like this, then so should they.
The failure you're describing is that your coworkers are not doing their job.
And if you accept "the LLM did that, not me" as an excuse then the failure is on you and it will keep happening.
Re:Two things LLM coding agents are still bad at
by worldsayshi on Thursday October 09, 2025 @08:46AM
(#45526900)
I think it goes without saying that we need to be sceptical when to use and not use LLM. The point I'm trying to make is more that we should have more validations and not that we should be less sceptical about LLMs.
Meticulousness shouldn't be an excuse to not have layers of validation that doesn't have to cost that much if done well.
I have already had to correct a LOT of crap similar to the above in refactoring-done-via-LLM over the last year.
When stuff like this was done by a plain, slow, organic human, it was far more accurate. And many times, completely accurate with no defects. Simply because many developers pay close attention when they are forced to do the manual labour themselves.
Sure the refactoring commit is produced faster with LLM assistance, but repeatedly reviewing code and pointing out weird defects is very stressful.