GPT-3 General Question Answering

I would like to explore using GPT-3 as a general question-answering resource.

Can anyone link to any systematic study of what GPT-3 knows or how successful it’s been on some general knowledge test?

Should I assume DaVinci with low temperature is the standard choice or is there an optimal set-up for the most accurate possible answers (along with sending examples in the prompt)?

If I decide to make it more domain-specific, what options are there for giving it the information? Do I have to pass it as the prompt, or can we train GPT on new information ourselves?

Thanks very much

1 Like

Thanks very much.
How would you fine-tune it to be domain-specific, if you decided to?

Thanks, got it. So there are no other functionalities about GPT-3 to know about in terms of special method parameters or going into the internals or anything like that. Everything you do has to just be through prompt customization, and fine-tuning just means providing examples guiding GPT in the direction you would like?

2 Likes