[{"data":1,"prerenderedAt":205},["ShallowReactive",2],{"DlFXI4Eibt_Bn9lrEZz1TYbHCWFZj3IvqwHQSEW-Exc":3,"MU-k_89h5DacnzLsRZgg83Tm-Fs_Hp7XdEhNESju-3A":194},{"code":4,"msg":5,"data":6},0,"",{"category":7,"tag":11,"hot":39,"new":78,"banner":118,"data":143,"cache":193},[8,9,10],"Agent","OpenAI","LLM",[12,14,17,20,23,25,27,30,33,36],{"title":8,"total":13},39,{"title":15,"total":16},"Google",44,{"title":18,"total":19},"Nvidia",13,{"title":21,"total":22},"Claude",11,{"title":9,"total":24},35,{"title":10,"total":26},85,{"title":28,"total":29},"DeepSeek",9,{"title":31,"total":32},"OCR",1,{"title":34,"total":35},"Chat",7,{"title":37,"total":38},"Generator",116,[40,48,55,64,71],{"id":41,"publish_date":42,"is_original":4,"collection":5,"cover_url":43,"cover_url_1_1":44,"title":45,"summary":46,"author":47},557,"2022-04-29","article_res/cover/7a9b1375ed9bb298154981bae42b794d.jpeg","article_res/cover/afa281dd52bc0454e6735daa8e6b0706.jpeg","Translation and summary of Messari Report [2.8 Kristin Smith, Blockchain Association and Katie Haun, a16z]","We need unity and speed right now.","Translation",{"id":49,"publish_date":50,"is_original":4,"collection":5,"cover_url":51,"cover_url_1_1":52,"title":53,"summary":54,"author":47},531,"2022-05-25","article_res/cover/e8362057f8fa189594c60afdfaaeb6e5.jpeg","article_res/cover/8ea08d0d6fa7eee6b57ed4ec61b61ad6.jpeg","Decentralized Society: Finding Web3’s Soul / Decentralized Society: Finding the Soul of Web3 -7","Decentralization through Pluralism When analyzing ecosystems, it's desirable to measure how decentralized it is.",{"id":56,"publish_date":57,"is_original":32,"collection":58,"cover_url":59,"cover_url_1_1":60,"title":61,"summary":62,"author":63},127,"2024-11-14","#Google #AI Game #World Model #AI Story","article_res/cover/0233a875b7ec2debf59779e311547569.jpeg","article_res/cover/6ffddb6ae4914b3c699493311aa9f198.jpeg","Google Launches \"Unbounded\": A Generative Infinite Character Life Simulation Game","Unbounded: A Generative Infinite Game of Character Life Simulation","Renee's Entrepreneurial Journey",{"id":13,"publish_date":65,"is_original":32,"collection":66,"cover_url":67,"cover_url_1_1":68,"title":69,"summary":70,"author":63},"2025-02-14","#Deep Dive into LLMs #Andrej Karpathy #LLM #Tool Use #Hallucination","article_res/cover/11e858ad6b74dfa80f923d549b62855c.jpeg","article_res/cover/615e1b320f1fc163edc1d2d154a6de33.jpeg","Andrej Karpathy's in-depth explanation of LLM (Part 4): Hallucinations","hallucinations, tool use, knowledge/working memory",{"id":72,"publish_date":73,"is_original":4,"collection":5,"cover_url":74,"cover_url_1_1":75,"title":76,"summary":77,"author":47},579,"2022-04-07","article_res/cover/39387376ba28447af1eb40576b9df215.jpeg","article_res/cover/02727ede8551ed49901d0abe6d6305b7.jpeg","Messari Report Translation and Summary 【1-7 Surviving the Winter】","I’d be more cautious here: 10 year and 10 hour thinking only.",[79,87,95,103,111],{"id":80,"publish_date":81,"is_original":32,"collection":82,"cover_url":83,"cover_url_1_1":84,"title":85,"summary":86,"author":63},627,"2025-03-20","#AI Avatar #AI Video Generation","article_res/cover/d95481358f73924989f8c4ee9c75d1c8.jpeg","article_res/cover/b74bc0fab01f8b6a6aa87696c0c3ed8b.jpeg","DisPose: Generating Animated Videos by Driving Video with Reference Images","DisPose is a controllable human image animation method that enhances video generation.",{"id":88,"publish_date":89,"is_original":32,"collection":90,"cover_url":91,"cover_url_1_1":92,"title":93,"summary":94,"author":63},626,"2025-03-21","#Deep Dive into LLMs #LLM #RL #Andrej Karpathy #AlphaGo","article_res/cover/446553a5c8f8f2f07d97b20eaee84e56.jpeg","article_res/cover/e6c2823409c9b34624064b9acbaca6f1.jpeg","AlphaGo and the Power of Reinforcement Learning - Andrej Karpathy's Deep Dive on LLMs (Part 9)","Simply learning from humans will never surpass human capabilities.",{"id":96,"publish_date":97,"is_original":32,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":63},625,"2025-03-22","#Deep Dive into LLMs #LLM #RL #RLHF #Andrej Karpathy","article_res/cover/8da81d38b1e5cf558a164710fd8a5389.jpeg","article_res/cover/96f028d76c362a99a0dd56389e8f7a9b.jpeg","Reinforcement Learning from Human Feedback (RLHF) - Andrej Karpathy's Deep Dive on LLMs (Part 10)","Fine-Tuning Language Models from Human Preferences",{"id":104,"publish_date":105,"is_original":32,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":63},624,"2025-03-23","#Deep Dive into LLMs #LLM #Andrej Karpathy #AI Agent #MMM","article_res/cover/a5e7c3d48bb09109684d6513287c661d.jpeg","article_res/cover/d3f22b7c0ab8d82fd2da457a299e0773.jpeg","The Future of Large Language Models - Andrej Karpathy's In-Depth Explanation of LLM (Part 11)","preview of things to come",{"id":112,"publish_date":105,"is_original":32,"collection":113,"cover_url":114,"cover_url_1_1":115,"title":116,"summary":117,"author":63},623,"#Google #Voe #AI Video Generation","article_res/cover/c44062fea0f336c2b96b3928292392c2.jpeg","article_res/cover/a041041c69092ad3db191c5bf3ff981b.jpeg","Trial of Google's video generation model VOE2","Our state-of-the-art video generation model",[119,127,135],{"id":120,"publish_date":121,"is_original":32,"collection":122,"cover_url":123,"cover_url_1_1":124,"title":125,"summary":126,"author":63},160,"2024-10-04","#Philosophy","article_res/cover/496990c49211e8b7f996b7d39c18168e.jpeg","article_res/cover/14dbaa1ade9cb4316d5829423a900362.jpeg","Time","The fungus of the morning does not know the waxing and waning of the moon, and the cicada does not know the seasons; this is a short life. To the south of the state of Chu there is a dark spirit which regards five hundred years as spring and five hundred years as autumn. In ancient times there was a great tree called the Ming which regarded eight thousand years as spring and eight thousand years as autumn; this is a long life.",{"id":128,"publish_date":129,"is_original":32,"collection":130,"cover_url":131,"cover_url_1_1":132,"title":133,"summary":134,"author":63},98,"2024-12-17","#AI Video Generator #Sora #Pika","article_res/cover/3b86e85d03fff4f356a3e4cf2bb329c9.jpeg","article_res/cover/5fa5c20ad0b40f8f544d257c0ef02938.jpeg","Pika 2.0 video generation officially released: effect comparison with Sora","今天，我们推出了Pika 2.0模型。卓越的文字对齐效果。惊人的视觉表现。还有✨场景成分✨",{"id":136,"publish_date":137,"is_original":32,"collection":138,"cover_url":139,"cover_url_1_1":140,"title":141,"summary":142,"author":63},71,"2025-01-14","#Nvidia #World Foundation Model #Cosmos #Physical AI #Embodied AI","article_res/cover/feddf8c832dfb45d28804291f6a42a9e.jpeg","article_res/cover/d6bc2f1186d96b78228c2283a17a3645.jpeg","NVIDIA's Cosmos World Model","Cosmos World Foundation Model Platform for Physical AI",[144,163,188],{"title":8,"items":145},[146,147,155],{"id":104,"publish_date":105,"is_original":32,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":63},{"id":148,"publish_date":149,"is_original":32,"collection":150,"cover_url":151,"cover_url_1_1":152,"title":153,"summary":154,"author":63},622,"2025-03-24","#OWL #AI Agent #MAS #MCP #CUA","article_res/cover/cb50ca7f2bf4d1ed50202d7406e1c19a.jpeg","article_res/cover/4aa7aa3badfacf3cc84121334f1050dd.jpeg","OWL: Multi-agent collaboration","OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation",{"id":156,"publish_date":157,"is_original":32,"collection":158,"cover_url":159,"cover_url_1_1":160,"title":161,"summary":162,"author":63},620,"2025-03-26","#LLM #Google #Gemini #AI Agent","article_res/cover/53751a6dbbe990b1eb0b63f3b062aed4.jpeg","article_res/cover/031344981f0a212ff82d1f3a64aa5756.jpeg","Gemini 2.5 Pro, claimed to be far ahead of the competition, has been released with great fanfare: comprehensively surpassing other LLMs and topping the global rankings","Gemini 2.5: Our most intelligent AI model",{"title":9,"items":164},[165,172,180],{"id":166,"publish_date":157,"is_original":32,"collection":167,"cover_url":168,"cover_url_1_1":169,"title":170,"summary":171,"author":63},619,"#OpenAI #AI Image Generator #4o #MMM #AR Transformer","article_res/cover/2faffc97fcecf3151552cb0fd3206d89.jpeg","article_res/cover/1133cb4948af44cee2e7fbe79efb69e5.jpeg","The native image function of GPT-4o is officially launched","Introducing 4o Image Generation",{"id":173,"publish_date":174,"is_original":4,"collection":175,"cover_url":176,"cover_url_1_1":177,"title":178,"summary":179,"author":63},434,"2023-07-15","#Anthropic #OpenAI #Google #AI Code Generator #Claude","article_res/cover/e1b6f600a2b9f262a4392684e5f2ce25.jpeg","article_res/cover/6e1772e83f78f9a351ab23d3e414adee.jpeg","Latest Updates on Google Bard /Anthropic Claude2 / ChatGPT Code Interpreter","We want our models to use their programming skills to provide more natural interfaces to the basic functions of our computers.  \n - OpenAI",{"id":181,"publish_date":182,"is_original":4,"collection":183,"cover_url":184,"cover_url_1_1":185,"title":186,"summary":187,"author":63},417,"2023-08-24","#OpenAI","article_res/cover/bccf897d50a88b18364e35f7466387e0.jpeg","article_res/cover/2f871085c1073717c1703ae86e18056f.jpeg","The GPT-3.5 Turbo fine-tuning (fine-tuning function) has been released～","Developers can now bring their own data to customize GPT-3.5 Turbo for their use cases.",{"title":10,"items":189},[190,191,192],{"id":88,"publish_date":89,"is_original":32,"collection":90,"cover_url":91,"cover_url_1_1":92,"title":93,"summary":94,"author":63},{"id":96,"publish_date":97,"is_original":32,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":63},{"id":104,"publish_date":105,"is_original":32,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":63},true,{"code":4,"msg":5,"data":195},{"id":196,"publish_date":197,"is_original":32,"collection":198,"articles_id":199,"cover_url":200,"cover_url_1_1":201,"title":202,"summary":203,"author":63,"content":204},99,"2024-12-16","#LLM #Meta","_i9GyqxIU3EWm8bmvq0nQw","article_res/cover/4375cc4fed9918f5b36c750f4acdc0a8.jpeg","article_res/cover/0bc09eb39451488370eb8dd005afb941.jpeg","Meta has introduced COCONUT, a continuous chain of thought, challenging traditional CoT and enhancing logical reasoning capabilities.","Is it as good as OpenAI's o1, though?","\u003Cdiv class=\"rich_media_content js_underline_content\n                       autoTypeSetting24psection\n            \" id=\"js_content\">\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;background-color: rgb(255, 255, 255);'>thought). Its core idea is to use the last hidden state of LLMs as the representation of the reasoning state (referred to as \"continuous thought\") instead of decoding it into word tokens. These continuous representations are directly fed back as the next input embedding, enabling reasoning in the continuous space.\u003C/p>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;background-color: rgb(255, 255, 255);'>Previously, the reasoning of large language models (LLMs) has been limited to the \"linguistic space,\" where the reasoning process is typically expressed through Chain of Thought (CoT) to solve complex problems. However, linguistic space is not always the optimal choice for reasoning. For example, most word tokens are primarily used to maintain textual coherence and are irrelevant to reasoning, while some key tokens require complex planning, posing significant challenges to LLMs.\u003C/p>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Comparison between CoT and Coconut\u003C/span>\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100008271\" data-ratio=\"0.30277777777777776\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423779997690.7188635109024801.png\">\u003C/p>\u003Ch3 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 20px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">CoT（Chain-of-Thought）\u003C/span>\u003C/h3>\u003Cul style='margin-top: 8px;margin-bottom: 8px;;padding-left: 25px;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;background-color: rgb(255, 255, 255);' class=\"list-paddingleft-1\">\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">Reasoning Mode: CoT expresses the reasoning process by generating a sequence of word tokens, for example: [x\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">Limitations:\u003C/section>\u003C/li>\u003Cul style=\"margin-top: 8px;margin-bottom: 8px;;list-style-type: square;padding-left: 25px;color: rgb(0, 0, 0);\" class=\"list-paddingleft-1\">\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">Reasoning is restricted to the \"language space.\"\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">Most word tokens are used to maintain text coherence but are not crucial to the reasoning process.\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">Key tokens may require complex planning, posing a challenge for LLMs.\u003C/section>\u003C/li>\u003C/ul>\u003C/ul>\u003Ch3 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 20px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Coconut（Chain of Continuous Thought）\u003C/span>\u003C/h3>\u003Cul style='margin-top: 8px;margin-bottom: 8px;;padding-left: 25px;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;background-color: rgb(255, 255, 255);' class=\"list-paddingleft-1\">\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">Reasoning patterns:\u003C/section>\u003C/li>\u003Cul style=\"margin-top: 8px;margin-bottom: 8px;;list-style-type: square;padding-left: 25px;color: rgb(0, 0, 0);\" class=\"list-paddingleft-1\">\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">The model's last hidden state is used as the representation of the reasoning state (referred to as \"continuous thinking\").\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">Directly use the \"continuous thinking\" as the embedding for the next step input instead of decoding it into word tokens.\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">Reasoning occurs in an unrestricted latent space rather than in linguistic space.\u003C/section>\u003C/li>\u003C/ul>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">Advantages:\u003C/section>\u003C/li>\u003Cul style=\"margin-top: 8px;margin-bottom: 8px;;list-style-type: square;padding-left: 25px;color: rgb(0, 0, 0);\" class=\"list-paddingleft-1\">\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">The model can explore multiple potential reasoning paths.\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">.\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">This avoids the limitation of prematurely determining a single path in traditional CoT.\u003C/section>\u003C/li>\u003C/ul>\u003C/ul>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;background-color: rgb(255, 255, 255);'>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 18px;font-weight: 700;letter-spacing: normal;text-align: left;background-color: rgb(255, 255, 255);'>An example of the location where continuous thought is decoded into language tokens\u003C/span>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100008274\" data-ratio=\"0.8768518518518519\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423779998010.6573560962201459.png\">\u003C/p>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;background-color: rgb(255, 255, 255);'>\u003Cspan style=\"font-size: 22px;;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Case Study: ProsQA\u003C/span>\u003C/p>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;background-color: rgb(255, 255, 255);'>The model trained with CoT fabricated an edge (\"every yumpus is a rempus\") when encountering a dead end. The path output by Coconut (k=1) ends with an unrelated node, whereas Coconut (k=2) correctly resolved the issue.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100008276\" data-ratio=\"0.49444444444444446\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423779997830.21095345945611443.png\">\u003C/p>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">The training process of Coconut\u003C/span>\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100008272\" data-ratio=\"0.3333333333333333\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423779997850.6412569480877932.png\">\u003C/p>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;background-color: rgb(255, 255, 255);'>In the training data containing language reasoning steps, additional chain-of-thoughts (e.g., c=1 in this case) are added at each training stage, and one language reasoning step is removed. Subsequently, the remaining language tokens (after the chain-of-thoughts) are trained using cross-entropy loss.\u003C/p>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Results of three datasets\u003C/span>\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100008273\" data-ratio=\"0.47314814814814815\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423779997920.5934247997403803.png\">\u003C/p>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;background-color: rgb(255, 255, 255);'>Comparison of GSM8k, ProntoQA, and ProsQA: Higher accuracy indicates stronger reasoning ability of the model, while generating fewer tokens represents higher reasoning efficiency.\u003C/p>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Selected X online netizen comments\u003C/span>\u003C/h2>\u003Cblockquote style='margin-top: 20px;margin-bottom: 20px;;padding: 10px 10px 10px 20px;border-top: 3px none rgba(0, 0, 0, 0.4);border-right: 3px none rgba(0, 0, 0, 0.4);border-bottom: 3px none rgba(0, 0, 0, 0.4);border-left-color: rgba(0, 0, 0, 0.4);border-radius: 0px;background: none 0% 0% / auto no-repeat scroll padding-box border-box rgba(0, 0, 0, 0.05);width: auto;height: auto;box-shadow: rgba(0, 0, 0, 0) 0px 0px 0px 0px;overflow: auto;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Cp style=\";line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">Changing the base often brings new insights. I feel like I just fell off a coconut tree. 😉\u003C/p>\u003C/blockquote>\u003Cblockquote style='margin-top: 20px;margin-bottom: 20px;;padding: 10px 10px 10px 20px;border-top: 3px none rgba(0, 0, 0, 0.4);border-right: 3px none rgba(0, 0, 0, 0.4);border-bottom: 3px none rgba(0, 0, 0, 0.4);border-left-color: rgba(0, 0, 0, 0.4);border-radius: 0px;background: none 0% 0% / auto no-repeat scroll padding-box border-box rgba(0, 0, 0, 0.05);width: auto;height: auto;box-shadow: rgba(0, 0, 0, 0) 0px 0px 0px 0px;overflow: auto;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Cp style=\";line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">Continuous thinking might redefine our understanding of emergent reasoning in AI.\u003C/p>\u003C/blockquote>\u003Cblockquote style='margin-top: 20px;margin-bottom: 20px;;padding: 10px 10px 10px 20px;border-top: 3px none rgba(0, 0, 0, 0.4);border-right: 3px none rgba(0, 0, 0, 0.4);border-bottom: 3px none rgba(0, 0, 0, 0.4);border-left-color: rgba(0, 0, 0, 0.4);border-radius: 0px;background: none 0% 0% / auto no-repeat scroll padding-box border-box rgba(0, 0, 0, 0.05);width: auto;height: auto;box-shadow: rgba(0, 0, 0, 0) 0px 0px 0px 0px;overflow: auto;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Cp style=\";line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">This is truly a very interesting development! The concept of continuous thinking is fascinating and could significantly enhance the reasoning capabilities of large language models (LLMs).\u003C/p>\u003C/blockquote>\u003Cblockquote style='margin-top: 20px;margin-bottom: 20px;;padding: 10px 10px 10px 20px;border-top: 3px none rgba(0, 0, 0, 0.4);border-right: 3px none rgba(0, 0, 0, 0.4);border-bottom: 3px none rgba(0, 0, 0, 0.4);border-left-color: rgba(0, 0, 0, 0.4);border-radius: 0px;background: none 0% 0% / auto no-repeat scroll padding-box border-box rgba(0, 0, 0, 0.05);width: auto;height: auto;box-shadow: rgba(0, 0, 0, 0) 0px 0px 0px 0px;overflow: auto;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Cp style=\";line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">One question leads to more questions.\u003C/p>\u003C/blockquote>\u003Cp>\u003Cbr>\u003C/p>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",1752585431437]