News for hackers. Stuff that matters.
Re:Show HN: Factual AI Q&A – Answers based on Huberman Lab t... by rileyt on Saturday December 17, 2022 @06:52PM (#34033532)
It's not fine tuned. You literally just add something like "if the answer to the question isn't in the context, say 'I don't know'" It's wild.
Re:Show HN: Factual AI Q&A – Answers based on Huberman Lab t... by oidar on Saturday December 17, 2022 @10:58PM (#34034923)
How did you do that?
Re:Show HN: Factual AI Q&A – Answers based on Huberman Lab t... by charcircuit on Sunday December 18, 2022 @06:02AM (#34036569)
He just told you? The prompt is a combination of the top 5 search results, the phrase to say it doesn't know if it does not have context, and the question the user is actually asking. That is sent to OpenAI and the response is shown along with the search results as the references.
Re:Show HN: Factual AI Q&A – Answers based on Huberman Lab t... by krashidov on Sunday December 18, 2022 @06:55PM (#34045996)
So do you have the entire Huberman podcast transcript in the context of the prompt?