In my experience the turbo models are significantly worse than the old GPT-4 models, especially in structured output and following instructions. I'm guessing its due to the cheapened attention mechanism, but its a bit disappointing that OpenAI tries and hides these limitations.
Are you really gonna hold up flying as an example of a "share" that works? Flying is notoriously a miserable experience, between security, delays, cramped seating...
Yeah, I mean, it'll get you to where you're going but it's not really an enjoyable experience.
