|
|
|
|
|
by agosz
695 days ago
|
|
I have tried using LLMs on the legacy C++ codebase that I work on, and the only thing it could reliably do was generate code for unit tests. When I fix bugs, it's usually not helpful because I need to debug and track down where the bug is. When I develop new features, it occasionally uses the wrong lock, or makes up APIs that don't exist. I find it gets in the way more for development. For C# and .NET core, I found IntelliCode to be pretty useful. |
|