It's sort of wild how different AI models are for coding. Some seems to do great and others I'm fighting it to do anything. What is your favorite model currently?
Commit
406eb3c
One thing I’m trying to separate is model quality from acceptance quality. In a recent migration, an input-editing regression only became obvious when we exercised the interaction.
When you compare models, do you give them the same explicit acceptance checks, or mostly judge the diff and final result?
commit 406eb3c