https://hackerpaper.kaipfister.de/p/2303.14617/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=36474029urn:hackerpapers:mention:2303.14617:36474029Mon, 26 Jun 2023 00:04:56 GMT<p>In every model I’ve worked with, all of those steps are EXPLICIT. You take input, then tokenize, then embed, feed to model, then convert from embeddings to tokens, then back to words. There’s actually a lot of work done in embedding space! Chained execution, neural graph reasoning (see https://arxiv.org/pdf/2303.14617.pdf), even basic IR tasks like clustering and retrieval. There’s been no real effort to especially expose it because that is what you get by default. Even OpenAI has an “embed” endpoint. So you’re not going to see a huge push for it the same way you won’t see a push for…</p><p><a href="https://hackerpaper.kaipfister.de/p/2303.14617/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.DB