Cross-Entropy Games for Language Models: From Implicit Knowledge to General Capability Measures · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2506.06832/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTCross-Entropy Games for Language Models: From Implicit Knowledge to General Capability Measures — mentioned by upperhalfplanehttps://news.ycombinator.com/item?id=44887346urn:hackerpapers:mention:2506.06832:44887346Wed, 13 Aug 2025 11:54:56 GMT<p>&gt; It&#x27;s basically always guessing / confabulating / hallucinating if you ask it an introspective question like that. You&#x27;re absolutely right! This is the basis of this recent paper https://www.arxiv.org/abs/2506.06832</p><p><a href="https://hackerpaper.kaipfister.de/p/2506.06832/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI