I’ve found coding assistance to be pretty lacklustre myself as well. That said, one area where language models might actually be good is emulating a type system for dynamic languages. Given how good these things are at figuring out general shape of the code, I suspect they could fairly accurately tell you argument and return types for functions. And you could probably get away with a pretty small model if it only targets a specific language.

For devops, it’s amazing. We use many tools that we are not experts in, and it’s incredible to get ready to use code examples how to configure them for various scenarios.

I save many hours every week using open Ai latest models.