Co-pilot is utterly useless. It uses 4o. It has not given me one correct answer.
Claude is better. I'd say about 50% useful. Still gives lots of syntactically wrong code but at least something that resembles something I can use.
Here's the problem though: You have to be a very, very, very good programmer to know when it is wrong. There is a mid-level developer (I wouldn't even call him that) on my project, he uses AI all the time, and he always trusts the answers. His code is a total ####ing mess. Often times it doesn't do what they ask, but he can't figure it out, so how the hell would he ever know if the AI did it properly? His part of the project has been on bug fixing for weeks now.
It's good for reference though. Yippee. A fancy SO.
__________________
If you don't pass this sig to ten of your friends, you will become an Oilers fan.
|