Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts

This is a quick prototype I built for semantic search and factual question answering using embeddings and GPT-3.


It tries to solve the LLM hallucination issue by guiding it only to answer questions from the given context instead of making things up. If you ask something not covered in an episode, it should say that it doesn't know rather than providing a plausible, but potentially incorrect response.


It uses Whisper to transcribe, text-embedding-ada-002 to embed, Pinecone.io to search, and text-davinci-003 to generate the answer.


More examples and explanations here: https://twitter.com/rileytomasek/status/1603854647575384067




Comments URL: https://news.ycombinator.com/item?id=34030389


Points: 7


# Comments: 2






from Hacker News: Front Page https://ift.tt/sMdAbUk

via IFTTT

Comments

Popular posts from this blog

Intentional dark pattern by Coinbase or just terrible UI?