We really need a model that can integrate with the LSP though - so it never generates LSP invalid code.
I think using the LSP is not just a trivial task of grabbing definitions using the LSP, there is context management and the speed at which inference works. On top of it, we also have to grab similar snippets from the surrounding code (open files) so we generate code which belongs to your codebase.
Lots of interesting challenges but its a really fun space to work on.