> I'm pretty sure it writes comments for itself, not for the user
Yeah, that sounds worse than "trying to helpful". Read the code instead, why add indirection in that way, just to be able to understand what other models understand without comments?
Yeah, I'm just doubtful Gemini could ever be considered a "better model" if it needs to put "chain of thought" artifacts into my source code, considering that none of the other models seems to need that to write better code than Gemini.
Yeah, that sounds worse than "trying to helpful". Read the code instead, why add indirection in that way, just to be able to understand what other models understand without comments?