It’s really good at writing bad code - something that superficially works but is badly architected, abstracted, or wrong in a subtle way.
Only a novice would look at ai code and say “wow this is good”.
Only a novice would look at ai code and say “wow this is good”.
Note that I am talking about frontier models and only the last 6-12 months. Opus was really the breakthrough point for me.
When you discuss design and architecture first, and write that out in a design doc or something along those lines, it works quite well for the most part.
And 9 out of 10 times when it produces some poor results, just asking "is this really a good approach?" or just stating "This code makes me very sad" it will most of the time do a really good job of analysing why that code is bad and how to improve it.
And you should know that this is not accurate. But at this point this has devolved into a dick measuring contest, which I refuse to do. Have a good day.
For a lot of problems "quick and good enough" is all that is required. I've used it a lot for managing my Home Assistant setup. Has saved me countless of hours.
In principle I could've done it myself, but I never would have, the time investment required to learn it wouldn't have been worth the value I get from it.
A pain plate of rice is bad food. But would you prefer starving too death? Or for others to starve?
Or saying that a car is a better vehicle than a bicycle. That is probably true, but many times for many people a bicycle is all they can get.