Hacker News new | past | comments | ask | show | jobs | submit login

" For example, a user might begin with a collection of thousands or even millions of books and PDFs, turn on some filters for specific features like “mention of geopolitical conflict” and “escalating rhetoric”, then quickly zoom in to the highlighted parts to find relevant passages and paragraphs. Compared to a conventional search that flattens all the detail into a single sorted list of a few dozen items, a heatmap lets the user see detail without getting lost in it. "

This already exists in a few Ask your PDF tools, and I haven't found it useful.

The problem in text is not discoverability. Order just matters too much in text. Just like how plucking exact match search results is about as useful as semantic search for 99% of use cases, the context matters. You either have something you want or you don't. The issue with semantic matching and trying to display or use that information is that you end up with a lot of blur and would be better of feeding such information to a GPT model to summarize, or simply using a GPT model initially, to construct something more useful for you to work with. Or in other words - semantic comparisons and grouping of content creates too much bloat compared to the reasoning currently possible by GPT models, and there is no solution to this here.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: