Hacker News new | ask | show | jobs
by vikp 1276 days ago
I don't think it's a huge lift to restrict a language model to "known" good facts from search results. And to have it cite sources.

I made a proof of concept this weekend - https://github.com/VikParuchuri/researcher . There are some issues, but it's very useful.
1 comments
hooande 1276 days ago
Fascinating. This isn't at all how ChatGPT works. You're not leveraging the scale of the internet + style transfer to provide answers. Instead it's doing text summarization on search results.

It's a very clever proof of concept. Not exactly a large language model.

link
vikp 1276 days ago
It's doing abstractive summarization over the search results, using GPT-3. The pipeline is:

  - Search using Google
  - Run some filters to exclude SEO spam, etc.
  - Scrape the pages that are returned
  - Find chunks of text likely to align with the answer (comparing embeddings)
  - Feed the most likely chunks into GPT-3 to get a summary
It is leveraging GPT-3 to produce better summaries, and it isn't purely extractive - the LLM uses context and knowledge to generate a better summary.

I want to experiment with a local model next, versus using GPT-3.

link