Which is still horrifically slow and unoptimized. I’m not sure why streaming tokens from an api into an electron app is difficult but OpenAI managed to bungle it somehow.
Interesting, and even wilder that it’s buggy like that. I get that desktop apps are probably not OpenAI’s expertise but the app is unfortunately pretty unusable most of the time as of the writing of this comment. You would think for the amount of money they pay their engineers something better would have been released.
Unusable in what way? I don't personally find the macOS app to be "unusable" at all.
Also, you may be underestimating how buggy Swift and the rest of Apple's stack are. It's hard to get those bugs resolved unless you happen to work at Apple. Thus, a lot of time is spent working around bugs up the stack. So I don't find it surprising that a company moving fast like OpenAI ships _some_ bugs. The mac app just came out this month? Give it time.
