{"id":5872,"date":"2025-07-03T23:05:26","date_gmt":"2025-07-03T15:05:26","guid":{"rendered":"https:\/\/infernews.com\/?page_id=5872"},"modified":"2025-07-04T04:48:31","modified_gmt":"2025-07-03T20:48:31","slug":"reasoning","status":"publish","type":"page","link":"https:\/\/infernews.com\/blog\/reasoning\/","title":{"rendered":"Reasoning"},"content":{"rendered":"<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"How AI Learned to Think\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_PvDaPeQjxOE\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FPvDaPeQjxOE%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/PvDaPeQjxOE\" \/><meta itemprop=\"duration\" content=\"PT17M24S\" \/><meta itemprop=\"uploadDate\" content=\"2024-11-11T19:32:39Z\" \/><\/div><div id=\"lyte_PvDaPeQjxOE\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FPvDaPeQjxOE%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">How AI Learned to Think<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/PvDaPeQjxOE\" rel=\"nofollow\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FPvDaPeQjxOE%2F0.jpg\" alt=\"How AI Learned to Think\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"World models, why do we need them? This video traces the research history that made it possible. When AI merged gameplay and language, everything changed... From chess engines that couldn&#039;t see beyond the next move, to AlphaGo&#039;s superhuman intuition, to Google&#039;s Genie 3 generating entire interactive worlds - this is the story of how AI learned to build world models. World models are simulators that predict how environments change in response to actions. They&#039;re the foundation behind everything from game-playing AI to modern reasoning systems to Google DeepMind&#039;s latest breakthrough. KEY MILESTONES COVERED: Early chess AI and handcrafted evaluation functions TD-Gammon: First neural networks learning position intuition (1989) AlphaGo: Combining learned intuition with Monte Carlo Tree Search (2016) World Models paper: Learning simulators from experience (2018) MuZero: General game playing with learned world models (2020) LLMs as universal world models Chain-of-thought reasoning as tree search over language Modern systems: OpenAI o1, Google Gemini, DeepSeek Google Genie 3: Interactive world generation (2025-2026) [follow up video in progress] This video examines how game-playing breakthroughs - particularly the convergence of MCTS with neural networks - transformed into today&#039;s reasoning capabilities and ultimately enabled systems like Genie 3 to dream up entire explorable worlds. Follow me: www.artoftheproblem.com\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"Transfer Reasoning to Llama 3.1 (Chess AI)\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_oRVDDztO6Ag\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FoRVDDztO6Ag%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/oRVDDztO6Ag\" \/><meta itemprop=\"duration\" content=\"PT29M39S\" \/><meta itemprop=\"uploadDate\" content=\"2025-07-03T14:01:21Z\" \/><\/div><div id=\"lyte_oRVDDztO6Ag\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FoRVDDztO6Ag%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">Transfer Reasoning to Llama 3.1 (Chess AI)<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/oRVDDztO6Ag\" rel=\"nofollow\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FoRVDDztO6Ag%2F0.jpg\" alt=\"Transfer Reasoning to Llama 3.1 (Chess AI)\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"Distilling Thought: Transferring Search-Based Reasoning to Small LMs. The Incredible Shrinking Mind: Is AI Reasoning Lost in Transfer? All rights w\/ authors: ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context Joongwon Kim 1,2, Anirudh Goyal 1 , Liang Tan 1, Hannaneh Hajishirzi 2, Srini Iyer 1, Tianlu Wang 1 from 1 AI at Meta, 2 University of Washington Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess Dongyoon Hwang 1\u2217 Hojoon Lee 1, Jaegul Choo 1, Dongmin Park 2, Jongho Park 2,3 from 1 KAIST 2 KRAFTON 3 UC Berkeley #airesearch #chess #aiexplained #newtechnology #reasoning\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"googlesitekit_rrm_CAowvqSiDA:productID":"","footnotes":""},"class_list":["post-5872","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/pages\/5872","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=5872"}],"version-history":[{"count":0,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/pages\/5872\/revisions"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=5872"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}