https://hackerpaper.kaipfister.de/p/2401.08741/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=47327788urn:hackerpapers:mention:2401.08741:47327788Tue, 10 Mar 2026 19:31:13 GMT<p>it also reminds me a bit of this diffusion paper [1] which proposes having an encoding layer and a decoding layer but repeats the middle layers until a fixed point is reached. but really there is a whole field of &quot;deep equilibrium models&quot; that is similar. it wouldn&#x27;t be surprising if large models develop similar circuits naturally when faced with enough data. finding them on the other hand is not easy! as you&#x27;ve shown, i guess brute force is one way.. it would be nice to find a short cut but unfortunately as your diagrams show, the landscape isn&#x27;t exactly smooth. I would also hypothesize that…</p><p><a href="https://hackerpaper.kaipfister.de/p/2401.08741/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV