Thumbs up, I totally missed this. Didn’t encounter this approach in the suggestions either.
That’s actually one reason why I don’t think it’s current incarnation is a good fit for learning new apis, it’s been trained on a lot of code, not all of it good.
Seems like something a future version might be able to fix, perhaps by training a new layer using just demonstrably ‘good’ code?
That’s actually one reason why I don’t think it’s current incarnation is a good fit for learning new apis, it’s been trained on a lot of code, not all of it good.
Seems like something a future version might be able to fix, perhaps by training a new layer using just demonstrably ‘good’ code?