Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2311.04254/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTEverything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation — mentioned by CGamesPlayhttps://news.ycombinator.com/item?id=38391128urn:hackerpapers:mention:2311.04254:38391128Thu, 23 Nov 2023 09:52:39 GMT<p>While we&#x27;re all wildly speculating about what Q* is and if GPT-5 will be able to do grade-school maths, I stumbled upon this interesting paper that discusses mixing classic RL algorithms (MCTS, like from AlphaGo), with LLMs. Q* is typically used to refer to the search for the optimal policy in these algorithms. Paper: &quot;Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation &quot; - https://arxiv.org/abs/2311.04254</p><p><a href="https://hackerpaper.kaipfister.de/p/2311.04254/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI