alt Hacker NewsThis just isn’t true at all, with guidance and guard rails they produce much better code than the average developer does. They are only going to get better.
This just isn’t true at all, with guidance and guard rails they produce much better code than the average developer does. They are only going to get better.
That is completely false in my experience. I have never once seen an LLM produce code that would be acceptable. It certainly is worse than what a human can do.