Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: HNRelevant – Add a "related" section to Hacker News

github.com

Post reply on HN
Print view View original

21–30 of 37 posts

Re: Show HN: HNRelevant – Add a "related" section to Hacker News

#24

Post by swyx »

can we use this thread to share other useful HN tooling?

mine is here: https://github.com/swyxio/hnx

- displays the latest links from Y Combinator's Hacker News

- Offers a link for submitting the url of the current tab.

- shows previous results when submitting in case someone recently submitted

Re: Show HN: HNRelevant – Add a "related" section to Hacker News

#25

Post by quantadev »

Thought Experiment: Imagine if we had a true "Perma-Web" where something like IPFS was keeping a permanent record of every web page. Then we could have a "Semantic Web" where each webpage maps to a single point (it's Vector Embedding) in higher dimensional space.

This would mean you could do things like:

1) Write a blog post, and then find all other blog posts that were the 'closest to yours' that was ever written.

2) Do basic "Search" in a way that's probably more powerful than even the Google Page-Rank Algo, by being able to look up every web page that exists based on a Cosine Similarity.

It's a shame Web3 didn't really ever "go viral" in a big way, or else we'd be able to do this stuff right now.

Re: Show HN: HNRelevant – Add a "related" section to Hacker News

#26

Post by never_inline »

quantadev wrote: post #25

Thought Experiment: Imagine if we had a true "Perma-Web" where something like IPFS was keeping a permanent record of every web page. Then we could have a "Semantic Web" where each webpage maps to a single point (it's Vector Embedding) in higher dimensional space. This would mean you could do things like: 1) Write a blog post, and then find all other blog posts that were the 'closest to yours' that was ever written. 2…

Cosine similarity alone can't give you good results. For example, if you want to search specific names or acronyms, cosine similarity won't help much.

People act like embeddings are all you need for search.

Curse of dimensionality also means what you think is the most similar is not necessarily the most similar thing in vector space. See the last Hn discussion on word embeddings for some examples.

Re: Show HN: HNRelevant – Add a "related" section to Hacker News

#27

Post by cosmicgadget »

quantadev wrote: post #25

Thought Experiment: Imagine if we had a true "Perma-Web" where something like IPFS was keeping a permanent record of every web page. Then we could have a "Semantic Web" where each webpage maps to a single point (it's Vector Embedding) in higher dimensional space. This would mean you could do things like: 1) Write a blog post, and then find all other blog posts that were the 'closest to yours' that was ever written. 2…

Not the exact implementation you suggest, but similar:

https://news.ycombinator.com/item?id=43797896

The idea is to then allow bloggers to link relevant posts so readers can easily traverse the web.

Re: Show HN: HNRelevant – Add a "related" section to Hacker News

#30

Post by quantadev »

cosmicgadget wrote: post #27
quantadev wrote: post #25

Thought Experiment: Imagine if we had a true "Perma-Web" where something like IPFS was keeping a permanent record of every web page. Then we could have a "Semantic Web" where each webpage maps to a single point (it's Vector Embedding) in higher dimensional space. This would mean you could do things like: 1) Write a blog post, and then find all other blog posts that were the 'closest to yours' that was ever written. 2…

Not the exact implementation you suggest, but similar: https://news.ycombinator.com/item?id=43797896 The idea is to then allow bloggers to link relevant posts so readers can easily traverse the web.

Lots of cool information there that's right in my wheelhouse, that I'll be going thru. thanks!
Post reply on HN