Coding is being positioned as place where generative AI is going to have a huge impact.
But a new study of 800 developers found GitHub Copilot did little to improve productivity, while introducing 41% more bugs into the code.
https://www.cio.com/article/3540579/devs-gaining-little-if-anything-from-ai-coding-assistants.html
It's crazy to take a "fixing its bugs" approach. An innately flawed body of code is not a sound basis: it's like deliberately setting out to use badly maintained legacy code written by a guy who got fired.
Discard it and write it yourself.