New top story on Hacker News: Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts
Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts
12 by rileyt | 2 comments on Hacker News.
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
December 18, 2022 at 01:05AM rileyt 12 https://ift.tt/98cNoDj Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts 2 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 https://ift.tt/TGCXYAW
12 by rileyt | 2 comments on Hacker News.
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
December 18, 2022 at 01:05AM rileyt 12 https://ift.tt/98cNoDj Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts 2 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 https://ift.tt/TGCXYAW
Nhận xét
Đăng nhận xét