I've been using Claude 3.7 for various things, including helping in game development tasks. The generated code usually requires editing and it can't do autonomously more than a few functions at once but it's a fairly useful tool in terms of productivity. And the logic part is also quite good, can design out various ideas/algorithms, and suggest some optimisations.
Tech stack is nothing fancy/rare but not the usual ReactJS slop either - it's C# with OpenGL.
I can't comment about the best practices though because my codebase follows none of them.
Yes, the user has to know enough to guide the AI when it's failing. So it can't exactly replace the programmer as it is now.
It really can't do niche stuff however - like SIMD. Maybe it would be better if I compiled a cheatsheet of .NET SIMD snippets and howtos because this stuff isn't really on the internet in a coherent form at all. So it's highly unlikely that it was trained on that.
Interesting - thanks! This isn't the type of tech stack where I'd have expected it to do very well, so the fact that you're at least finding it to be productive is encouraging, although the (only) "function level competency" is similar to what I've experienced - enough to not have been encouraged to try anything more complex.