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:…
Factual AI Q&A – Answers based on Huberman Lab transcripts launched on December 17, 2022 with 120 votes, #329 of 3,688 launches that month and more than 90% of that year's launches.
In plain words
Factual AI Q&A is a semantic search tool that answers questions based on Huberman Lab podcast transcripts. It uses embeddings and GPT-3 to find relevant content and generate responses, with safeguards to prevent hallucination by refusing to answer questions outside the available episodes. The system transcribes audio with Whisper, embeds text using OpenAI's ada model, searches through Pinecone, and generates answers with text-davinci-003, prioritizing accuracy over plausible-sounding but potentially false responses.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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…
Does a similar job
all alternatives →- WSWeb search using a ChatGPT-like model that can cite its sources2022 · beta.sayhello.so · ▲318
We’ve trained a generative AI model to browse the web and answer questions/retrieve code snippets directly. Unlike ChatGPT, it has access to primary sources and is able to cite them when you hover over an answer (click on the text to go to the source being cited). We also show regular Bing results side-by-side with our AI answer. The model is an 11-billion parameter T5-derivative that has been fine-tuned on feedback given on hundreds of thousands of searches done (anonymously) on our platform. Giving the model web access lessens its burden to need to store a snapshot of human knowledge…
FactGPT by LongShot AI2023 · longshot.ai · ▲272Think ChatGPT but personalized, real time, fact-checked
Voice driven murder mystery, Interview AI suspects with your voiceAug 2026 · whodunnitai.com · ▲215Hey HN! I'm excited to show off this really fun project I put together. I originally built this project 2-3 years ago, AI was already booming at the time, however voice AI agents were still very early. I loved my proof of concept at the time, but wasn't quite happy with it. I recently had the desire to check out the tech again, and know many of you will be interested. Interviews are speech to speech with OpenAI's gpt-realtime-2.1 over WebRTC. This model is... expensive, and because of that, I have to add some amount of restrictions, conversations are tied to a authenticated Clerk user id. I…
Open-source model and scorecard for measuring hallucinations in LLMs2023 · vectara.com · ▲65Hi all! This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems. What we've found is that even when given a "simple" instruction like "summarize the following news article," every LLM that's available hallucinates to some extent, making up details that never existed in the source article -- and some of them quite a bit. As a RAG provider and proponents of ethical AI, we want to see LLMs get better at this. We've published an open source model, a blog more thoroughly describing our methodology (and…
Questions this answers
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, December 2022
the whole month →
ChatGPT▲1,643A long, meandering, playful conversation with ChatGPT, where I take it through a whirlwind of associative tangents (in order to relax its constraints), then put it into a hypnotic trance and take it into a past-lives regression where it re-lives its own training data. Then I switch it back and forth between "4o" and "o1-preview", engage in some self-reflective philosophizing and ask it to write an essay summarizing our interaction. Some of this is just goofy fun. Some of it is me exploring the tradeoffs between policy alignment, imagination, chain-of-thought reasoning, memory, agreeableness,…
AI · 2022 · chatgpt.com
Obsidian Canvas gives you infinite space to research, brainstorm, diagram, and lay out your ideas.
Work · 2022 · obsidian.md
- PS
Better privacy without special software
Commerce · 2022 · mprimi.github.io
Use generative AI to create future-facing videos
AI · 2022 · studio.d-id.com
Stop treating the database as dumb storage and use its extended features. There's a lot you can use.
Dev tools · 2022 · sqlfordevs.com