{"slug": "ask-hn-why-are-llms-so-bad-at-board-games", "title": "Ask HN: Why are LLMs so bad at board games?", "summary": "A user on Hacker News reports that large language models consistently fail to understand board game rules, raising concerns about fundamental limitations in AI reasoning. Despite rulebooks being self-contained, LLMs cannot answer basic questions or play games, highlighting a gap in current AI capabilities.", "body_md": "| ||||||||||||\n2 points by |\nI've come across a use case LLMs seem inexplicably bad at: reading and understanding board game rules. It seems like it should be something an LLM would be excellent at. After all, a rulebook is just a self contained set of instructions. And yet, not only do LLMs fail to play a board game, I have yet to get one to successfully understand a rulebook enough to even answer basic rules questions. This seems like a massive red flag overall for the status of AI. I'm wondering if this is an overcomeable issue, or if it speaks to the underlying limitations of AI in general. | |||||||||||\n|", "url": "https://wpnews.pro/news/ask-hn-why-are-llms-so-bad-at-board-games", "canonical_source": "https://news.ycombinator.com/item?id=48556974", "published_at": "2026-06-16 15:39:16+00:00", "updated_at": "2026-06-16 15:48:58.577465+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-research", "ai-ethics"], "entities": ["Hacker News"], "alternates": {"html": "https://wpnews.pro/news/ask-hn-why-are-llms-so-bad-at-board-games", "markdown": "https://wpnews.pro/news/ask-hn-why-are-llms-so-bad-at-board-games.md", "text": "https://wpnews.pro/news/ask-hn-why-are-llms-so-bad-at-board-games.txt", "jsonld": "https://wpnews.pro/news/ask-hn-why-are-llms-so-bad-at-board-games.jsonld"}}