Use GPT-3 incorrectly: reduce costs 40x and increase speed by 5x

Re:Use GPT-3 incorrectly: reduce costs 40x and increase spee... by timfsu on Wednesday February 08, 2023 @12:23AM (#34704452)

This is great, thanks for sharing. I've been pretty reluctant to use davinci in production due to costs, but the other models seem significantly less capable. It seems like there's still a lot to learn about working with these models at scale.

[ Parent | on HN ]

Re:Use GPT-3 incorrectly: reduce costs 40x and increase spee... by Buoy on Wednesday February 08, 2023 @12:28AM (#34704485)

Yes definitely give this a go, for us with our use case davinci is prohibitively expensive in production so we literally cannot use it given the number of requests we make - interestingly I saw some OpenAI documentation the other day at the YC event which basically said that with a large enough dataset (I recall >= 30k examples) all of the models (yes even ada) start to behave with similar performance, so bear that in mind!

[ Parent | on HN ]

Re:Use GPT-3 incorrectly: reduce costs 40x and increase spee... by jrvarela56 on Wednesday February 08, 2023 @08:53AM (#34708008)

My impression is that the workflow is supposed to be davinci for prototyping, then fine-tuning and downgrading to curie in several steps as you polish prompts and breakdown tasks (see https://github.com/openai/openai-cookbook/blob/main/techniqu...).

I haven't gotten beyond the davinci for prototyping tho. It's cheap enough that a month of tinkering a chatbot was $7 in jan.

[ Parent | on HN ]