2,079 karma · joined October 28, 2016
The real complicated "bugs" often come from unclear requirements and the hard part is clearing up the requirements. It's more about design than logic errors in the code. And LLMs suck hard at this.
This whole argument is absolutely meaningless.
edit: just pointing out I'm not directly replying to you but to the whole thread.
I've rewritten several of such projects, successfully reduced complexity and improved performances just by knowing what I am doing.
Are we living on the same planet? I haven't seen much real progress since the release of chatGPT. Sure brenchmarks and graphs are going up, but in practice, meh...
Reminds me of all these YouTubers making video essays parotting something they have just learned, without actually mastering the subject.
Everyone complains about enshittification (YouTube ads, subscription models etc..), but then refuse to pay the real price premium goods and services cost. You get what you pay for.