Hacker News Reader

Horse and Astronaut are more closely connected (through the shows, road, actors) than Cancer and Healthcare which are not connected at all, apparently. This was the problem with public datasets and counting on HTML links to build the graph of human knowledge years ago. I tried to build better search at the time and hit this wall. Large language models will be a bonanza for new products now that the wall is broken.

View on HN

To be clear - the point is not to display what can or cannot be connected. The emphasis on this project is about the long and tortuous path chosen.

I take your point about the limits of knowledge graphs written manually vs LLMs. IMHO it's not either/or. We need both curation and statistical approaches, and when they are merged they give the best results. Just ask Wolfram: https://writings.stephenwolfram.com/2023/03/chatgpt-gets-its... Edit: fixed link to Stephen Wolfram's blog.

Reply on news.ycombinator.com