Show HN: I mapped HN's favorite books with GPT-4o • Hacker News Board

Re: Show HN: I mapped HN's favorite books with GPT-4o

#61

Post by lucius_verus » Tue, Sep 10, 2024, 9:37 PM UTC

Should we be concerned that Mein Kampf shows up in a list of HN "favorite books"?

Re: Show HN: I mapped HN's favorite books with GPT-4o

#62

Post by vismit2000 » Wed, Sep 11, 2024, 5:31 AM UTC

pstorm wrote: post #21

Fyi regarding cover images: I have built and run a handful of book related websites and Amazon is the easiest place I found to get book covers. You just need the Amazon id and every image is a standard url.

Fully agree with this. We built this LLM based book summary app: https://www.booksummary.pro/

The links here directly refer to images on Amazon (e.g. https://m.media-amazon.com/images/I/81YkqyaFVEL._SL1500_.jpg)

Re: Show HN: I mapped HN's favorite books with GPT-4o

#63

Post by dcchambers » Wed, Sep 11, 2024, 8:02 PM UTC

This is great, thanks for sharing! Seems like the perfect fun little project that before LLMs could take some serious data work, but LLMs make pretty trivial to process and create.

Re: Show HN: I mapped HN's favorite books with GPT-4o

#64

Post by fruktmix » Thu, Sep 12, 2024, 4:56 AM UTC

Did this project cost you anything to complete?

Re: Show HN: I mapped HN's favorite books with GPT-4o

#65

Post by maCDzP » Wed, Sep 18, 2024, 5:42 PM UTC

pmaze wrote: post #59

maCDzP wrote: post #53

Did you reduce the dimension before applying HDBSCAN?

I did, there was a first round of UMAP to 50 dimensions. Running HDBSCAN on the full embeddings gave bad results, lots of singleton clusters.

Interesting, I got the opposite result. The full embeddings gave two or three clusters. How did you work with the hyper parameters of HDBSCAN?