https://hackerpaper.kaipfister.de/p/2410.22071/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=47937960urn:hackerpapers:mention:2410.22071:47937960Tue, 28 Apr 2026 17:52:10 GMT<p>There has been quite a lot of work in this area. Analysis of activations around hallucinations seems to show that there is some representation of not knowing. There are things like https://arxiv.org/abs/2410.22071v2 But again things are not quite so simple. Detecting hallucinations might yield representations where it knew the answer but elected to hallucinate anyway because of some other obscure interaction. Anthropics work on autoencoding activations for analysis has yielded a lot of information about the inner semantic information on models. I haven&#x27;t seen a lot on bounds of knowledge…</p><p><a href="https://hackerpaper.kaipfister.de/p/2410.22071/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CLhttps://news.ycombinator.com/item?id=42323353urn:hackerpapers:submission:2410.22071:42323353Wed, 04 Dec 2024 23:55:03 GMT<p>Distinguishing Ignorance from Error in LLM Hallucinations</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2410.22071/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CLhttps://news.ycombinator.com/item?id=42087557urn:hackerpapers:submission:2410.22071:42087557Fri, 08 Nov 2024 15:29:07 GMT<p>Distinguishing Ignorance from Error in LLM Hallucinations</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2410.22071/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL