I guess you're using ChatGPT 3.5? I'd have thought v4 is simply too slow and you'd be unavoidably jolted out of flow waiting for it.

Both. v4 is fast during periods of low load, it is slower now than when I first got access. My usage patterns have shifted because of this, so I write longer prompts, have it do more work and switch to different tab. I'd pay more than twice as much to have it be at least 50% faster.