Once thing I've noticed is the difference in code quality by language. I'm constantly disappointed by the output of python code. I have to correct it to follow even the most basic software development principles (DRY, etc).

Typescript on the other hand, seems to do much better on first pass. Still not always beautiful code, but much more application ready.

My hypothesis is that this is due to the billions LOC of Jupyter Notebook it was probably trained on :/

With Typescript, I find it pretty eager to just try `(foo as any).bar` when it gets the initial typing wrong. It also likes to redefine types in every file they're used instead of importing.

It will fix those if you catch them, but I haven't been able to figure out a prompt that prevents this in the first place.

There's a LOT of bad/newbie Python code floating around. I find that if I'm specific, it does a good job. (I'm also passing in my code/notebooks as context, so one would assume that it is attempting to mirror my style.)