[{"data":1,"prerenderedAt":205},["ShallowReactive",2],{"DlFXI4Eibt_Bn9lrEZz1TYbHCWFZj3IvqwHQSEW-Exc":3,"EYMvIes5LpDpgASZ962C2gkGwjT_Hpa9dMvOVSu5XKU":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},93,"2024-12-22","#ChatGPT #LLM #o3","FvDH8zx68Pk37OSNFWdmSA","article_res/cover/9a82cf03cb3440e27d1a75b05028c8e8.jpeg","article_res/cover/701166cfa76bc3ccffb5ce9903e3a8a7.jpeg","I haven't figured out OpenAI Day 12 o1 yet, and o3 has already come.","OpenAI o3 and o3-mini—12 Days of OpenAI: Day 12","\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);'>In the early hours of today, OpenAI announced two models—o3 and o3 Mini.\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);'>2 is one of its important brands.\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);'>o3 is a highly intelligent model, while o3 Mini, although slightly less powerful, excels in balancing cost and performance.\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);'>\u003Cspan style=\"font-size: 22px;font-weight: bold;letter-spacing: 0em;\">The powerful capabilities of o3\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);'>o3 is a model that performs exceptionally well on many technical benchmarks.\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;\">Programming\u003C/span>\u003C/h3>\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 \"SWE Bench Verified\" benchmark, which includes real-world software development tasks, o3 achieved an accuracy rate of 71.7%, more than 20% higher than our o1 model. This means we have made significant strides in practicality.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008466\" data-ratio=\"0.9311827956989247\" data-s=\"300,640\" data-type=\"png\" data-w=\"930\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772548420.9236597384425176.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 terms of programming competitions, o1 reached an ELO score of 1891 on the \"Codeforces\" platform, while under the strongest computational settings, o3's ELO score has approached 2727. For comparison, Mark in the video had a best score of around 2500, and Yakob, the Chief Scientist at OpenAI, also did not exceed 2500. It seems that only one person at OpenAI has broken the 3000 mark.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008467\" data-ratio=\"0.9976580796252927\" data-s=\"300,640\" data-type=\"png\" data-w=\"854\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772549130.5898249469086629.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;\">Mathematics\u003C/span>\u003C/h3>\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 mathematics competition benchmark, o3 achieved an accuracy rate of 96.7%, compared to 83.3% for o1. In the AIME (American Invitational Mathematics Examination), Mark in the video indeed scored a perfect score once, but this time o3 missed only one question almost every time.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008468\" data-ratio=\"0.9727385377942999\" data-s=\"300,640\" data-type=\"png\" data-w=\"807\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772548470.1934639705434349.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);'>GPQA Diamond is a very challenging benchmark that measures a model's performance on doctoral-level scientific questions. o3 performed exceptionally well, achieving 87.7%, about 10% higher than o1's 78%. To give you a better sense, expert-level PhDs typically score around 70% in their specialized fields.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008469\" data-ratio=\"0.9963636363636363\" data-s=\"300,640\" data-type=\"png\" data-w=\"825\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772548580.6570130464383432.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);'>EpochAI is a new frontier in mathematical benchmarks. The scores on this test are much lower compared to other benchmarks, as it is considered the most difficult mathematical test currently. It includes many new, unpublished datasets with problems ranging from very difficult to extremely difficult. Some of these problems can take professional mathematicians hours or even days to solve. Currently, all publicly available models score less than 2% accuracy on this benchmark. However, o3 has managed to achieve over 25% accuracy.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008470\" data-ratio=\"1.040590405904059\" data-s=\"300,640\" data-type=\"png\" data-w=\"813\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772548570.3162609995419656.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;\">AGI\u003C/span>\u003C/h3>\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 first version of ARC-AGI took five years to improve from 0% to 5% accuracy, while o3, with low computational resources, achieved a new score of 75.7% on the semi-private holdout set of ARC AGI, becoming the latest top performer on ARC AGI. When o3 is allowed to perform long inference and with increased computational resources, it reaches 87.5% accuracy on the same dataset. For comparison, human performance on this task is around 85%.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008475\" data-ratio=\"0.5388888888888889\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772550280.22949574438293618.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;\">New breakthroughs in the ARC-AGI benchmark\u003C/span>\u003C/h2>\u003Cp style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;background-color: rgb(255, 255, 255);'>I remember learning from Professor Wu, a leading AI researcher in Japan, who said that due to resource constraints, researchers in institutions should focus more on creating AI benchmarks rather than just improving models. Current benchmarks are no longer sufficient to demonstrate the intelligence of LLMs. Some benchmark results are already approaching saturation, or are close to it. More challenging benchmarks are needed to accurately assess the capabilities of our cutting-edge models.\u003C/p>\u003Cp style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;background-color: rgb(255, 255, 255);'>ARC Prize is a non-profit organization dedicated to advancing AGI (Artificial General Intelligence) through benchmarking. The first benchmark, ARC-AGI, was proposed by François Chollet in his paper on measuring intelligence in 2019. However, it has remained the leading benchmark for five years, which is almost equivalent to \"centuries\" in the AI world. Therefore, any system that surpasses ARC-AGI would be a significant milestone toward general intelligence.\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;\">For example 🌰\u003C/span>\u003C/h3>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008471\" data-ratio=\"0.287962962962963\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772561780.4905541261920239.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cbr>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008472\" data-ratio=\"0.5703703703703704\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772550330.5690464068096566.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);'>This is a task that human teams can accomplish, but current AI has not yet been able to do so.\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);'>As mentioned above, the uniqueness of ARC-AGI lies in the fact that each task requires different skills. This means that the tasks are not simply repeating a memorized pattern, but require the AI to quickly learn and solve new problems. The purpose of ARC-AGI is to test a model's ability to learn new skills, rather than just remembering existing solutions.\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;\">o3 Mini\u003C/span>\u003C/h2>\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);'>o3 Mini will support three different inference effort settings: low, medium, and high. Users can freely adjust the inference time according to different use cases. For example, complex problems may require longer inference times, while simpler problems can be solved with shorter inference times.\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;\">Programming\u003C/span>\u003C/h3>\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);'>Codeforces ELO measures a programmer's ability, with higher scores indicating better performance. As shown in the chart, as the inference time increases, the performance of o3 Mini gradually improves, and even at medium inference time, it outperforms o1 Mini. This means that with the speed and cost provided by o3 Mini, it can achieve better performance in programming tasks compared to o1 Mini.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008476\" data-ratio=\"0.6083333333333333\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772561770.6930746659697644.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);'>Although o3 Mini still falls short of the best performance at ultra-high inference effort, it offers a good cost-benefit ratio. The following graph shows the trade-off between the estimated cost and Codeforces ELO score for o3 Mini in programming tasks.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008477\" data-ratio=\"0.7690655209452202\" data-s=\"300,640\" data-type=\"png\" data-w=\"931\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772552820.5386259716725306.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;\">Mathematics\u003C/span>\u003C/h3>\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);'>On the AIME 2024 dataset, o3 Mini performs comparably to o1 Mini in low inference mode, and in medium inference mode, it even outperforms o1 Mini. In high inference mode, the performance of o3 Mini further improves.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008478\" data-ratio=\"0.6370370370370371\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772548780.47814343086453537.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 low inference mode, o3 Mini significantly reduces the latency of o1 Mini, nearly matching the response speed of GPT-4, which is less than a second, almost instantaneous. Additionally, the latency of o3 Mini in medium inference mode is only half that of o1 Mini.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100008479\" data-ratio=\"0.6694444444444444\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423772561090.5334081131786739.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;\">Open Safety Testing\u003C/span>\u003C/h2>\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);'>Opening safety testing to external security researchers. Application form: https://openai.com/index/early-access-for-safety-testing/\u003C/p>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",1752585423958]