https://hackerpaper.kaipfister.de/p/1709.04574/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=17655046urn:hackerpapers:mention:1709.04574:17655046Tue, 31 Jul 2018 17:19:14 GMT<p>&gt; Qualitative items such as the ones listed are important for customer focused environments, however, I&#x27;m not sure if AI can account for such factors. One of the nice things you can do with optimization problems is plug humans into the loop as oracles. Often, &#x27;we know it when we see it&#x27;, and we can do pairwise comparisons of 2 possibilities. So you can train a ML model based on win/loss comparisons and it&#x27;ll learn to take into account the softer qualitative aspects via preference learning. A recent example you might remember from the press: &quot;Deep reinforcement learning from human preferences&quot;…</p><p><a href="https://hackerpaper.kaipfister.de/p/1709.04574/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.HChttps://news.ycombinator.com/item?id=16386267urn:hackerpapers:submission:1709.04574:16386267Thu, 15 Feb 2018 18:21:50 GMT<p>Adapting AI behavior using neural signatures of subjective interest</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1709.04574/">Paper and source history</a>. A submission is not an endorsement.</p>cs.HC