Comment by andrepd
14 hours ago
> my cognitive surrender to the model is increasing too. Why check it? It's obviously going to be correct.
I use "frontier" AI models daily at day_job. I can confidently say that anyone who is satisfied with the output of LLM code (enough to commit it straight off) is just an absolutely shit programmer. Sorry but I don't have any other way to put it.
The code is (with rare exceptions) atrocious on every level. It is only not atrocious if you take multiple iterations of "review and correct".
>If we find no flaws in the design whatsoever, will we be less careful about the second one? The third one? What about the ten thousandth one?
Like the saying goes, if my grandmother had wheels she would have been a bike. LLMs can't even produce quality maintainable code for a trivial web service or whatever. Why are we planning for what we will do when they can "design" 10,000 nuclear power plants without any flaw?
Yeah I was honestly stunned to read “obviously the code is going to be correct so why check it” be the most upvoted comment on this website. Are we even using the same product? These things constantly shit out plausible code that is riddled with errors and bad ideas. if you just copy, paste, and run without looking there’s gotta be a 30% rate of failure to run, piles of terminal errors.
Do programmers use this website anymore? Me, myself, I am a DOGSHIT amateur programmer and even I can tell these things are terrible without constant revision and oversight.