https://hackerpaper.kaipfister.de/p/2305.12517/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=37362263urn:hackerpapers:mention:2305.12517:37362263Sat, 02 Sep 2023 15:17:00 GMT<p>A little late to the party here, but text embeddings (at least the ones used in this blog post) generally aren&#x27;t very good at &quot;searching by vibes&quot;: they more compare by overlapping words or look for similar content to the search query. However, there is a recent paper that actually does try and do this: &quot;Retrieving Texts based on Abstract Descriptions&quot; (Ravfogel et al., 2023) https://arxiv.org/abs/2305.12517. They give many examples of searching by vibes: &quot;an architect designing a building&quot;, &quot;a company which is part of another company&quot;, &quot;a book that influenced the development of a genre&quot;…</p><p><a href="https://hackerpaper.kaipfister.de/p/2305.12517/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL