How do these compare to the recent Default ("turbo") vs legacy" (for plus/pro) modes?
If "turbo" is "gpt-3.5-turbo", how to access the (better?) "legacy" by API?
If "turbo" is "gpt-3.5-turbo", how to access the (better?) "legacy" by API?
I get the impression that until there is a significant amount of excess capacity, they will not put out new larger/slower models, so the only way you get a better one is if they can still make the next ChatGPT model release just as fast/"lightweight".
My suggestion is to find specific abilities that seem to be lacking in Turbo, and try to get a message to OpenAI staff about it with a request to attempt to improve the next ChatGPT model in that way.
Having said all of that, text-davinci-003 is still available.