[{"data":1,"prerenderedAt":383},["ShallowReactive",2],{"$fgukOamtKU1RtUiMFsqdObttmqPPQz0uc7bl_gj_LyX0":3,"$fK2TJ2QmGZ2UE-O30-GFFi4Se8q8pig_lxKo3I6T6RgY":245,"article-284":382},{"code":4,"msg":5,"data":6},0,"",{"category":7,"tag":11,"popular":19,"latest":86,"banner":126,"list":151,"cache":244},[8,9,10],"Agent","OpenAI","LLM",[8,12,13,14,9,10,15,16,17,18],"Google","Nvidia","Claude","DeepSeek","OCR","Chat","Generator",[20,29,37,45,54,62,70,79],{"id":21,"publish_date":22,"is_original":23,"collection":5,"cover_url":24,"cover_url_1_1":25,"title":26,"summary":27,"author":28},411,"2023-09-10",1,"article_res/cover/451ef50c225a8dc61c4336506794d13b.jpeg","article_res/cover/3ba9dc7a72f87d40b20fc2d225289ee3.jpeg","Idealism","Reality is created by the mind, we can change our reality by changing our mind. - Plato","Renee's Entrepreneurial Journey",{"id":30,"publish_date":31,"is_original":23,"collection":32,"cover_url":33,"cover_url_1_1":34,"title":35,"summary":36,"author":28},108,"2024-12-07","#LLM #AGI #AI Agent","article_res/cover/0039044422e4ec9f61c18e8ee1693bb0.jpeg","article_res/cover/4220971b108a91d21407d87bb02fbaa6.jpeg","Freysa.ai: The World's First Adversarial AI Agent Game","说服 Freysa 把钱包里的钱都拿出来",{"id":38,"publish_date":39,"is_original":23,"collection":40,"cover_url":41,"cover_url_1_1":42,"title":43,"summary":44,"author":28},12,"2025-03-09","#Oxford #Reasoning #LLM #Tool Use","article_res/cover/d448e9b3617a0b5302e1bd10c438bca9.jpeg","article_res/cover/864a468f9cc4c9317efadb3811909888.jpeg","Agentic Reasoning Framework - Significantly enhance the reasoning ability of LLMs through the integration of external tools using agents","Agentic Reasoning: Reasoning LLMs with Tools for Deep Research",{"id":46,"publish_date":47,"is_original":4,"collection":48,"cover_url":49,"cover_url_1_1":50,"title":51,"summary":52,"author":53},480,"2023-04-14","#Stable Diffusion","article_res/cover/0bdbe7cb1de4a78e54536e5d9afa7ec9.jpeg","article_res/cover/b3d6ffec0608dcfaf18c5a69906d1490.jpeg","【AIGC Learning】Generate Prompts Using Word Graphs - Stable Diffusion Web UI Series 13","AI will become a powerful tool in education, transforming the way we learn and deliver instruction.  \n- Reid Hoffman","--",{"id":55,"publish_date":56,"is_original":4,"collection":57,"cover_url":58,"cover_url_1_1":59,"title":60,"summary":61,"author":28},413,"2023-09-08","#Neuroscience","article_res/cover/74f8302d78a23d9430f22171eae136b6.jpeg","article_res/cover/87ca08af81bb304746be5261160964c0.jpeg","Can machines be conscious?","Do we have an ethical obligation to not turn off conscious machines? Would turning them off be murder? No. I don't lose any sleep over unplugging a conscious machine.\n- Jeff Hawkins, \"A Thousand Brains\"",{"id":63,"publish_date":64,"is_original":23,"collection":65,"cover_url":66,"cover_url_1_1":67,"title":68,"summary":69,"author":28},178,"2024-09-09","#Entrepreneurship","article_res/cover/a7224f025b55d1820408085faef63079.jpeg","article_res/cover/11a9995b096cbf64465ef01b8673b154.jpeg","37signals company","This damn sense of relaxation",{"id":71,"publish_date":72,"is_original":4,"collection":73,"cover_url":74,"cover_url_1_1":75,"title":76,"summary":77,"author":78},460,"2023-05-12","#Google","article_res/cover/b970687b12faa52da976f91248c2aa7b.jpeg","article_res/cover/d1e71b52cfd2c63bc6e71f3e85ff135c.jpeg","Learn what BRC-20 and Ordinals are using Google Bard","Ordinals - a new protocol that allows users to store arbitrary data on the Bitcoin blockchain","Google Bard mainly writes",{"id":80,"publish_date":81,"is_original":23,"collection":5,"cover_url":82,"cover_url_1_1":83,"title":84,"summary":85,"author":28},309,"2024-03-26","article_res/cover/9877f95894ee88532d0e6012c23a2df3.jpeg","article_res/cover/20092164ddc109ce6ae56b1984246751.jpeg","Learning the Cancun Upgrade with lepton and perplexity","Building a quick conversation-based search demo with Lepton AI.",[87,95,103,111,119],{"id":88,"publish_date":89,"is_original":23,"collection":90,"cover_url":91,"cover_url_1_1":92,"title":93,"summary":94,"author":28},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":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},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":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},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":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},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":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},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",[127,135,143],{"id":128,"publish_date":129,"is_original":23,"collection":130,"cover_url":131,"cover_url_1_1":132,"title":133,"summary":134,"author":28},300,"2024-04-16","#AI in Science #AGI","article_res/cover/6bf01e793e0f33e848572412eebdf9b0.jpeg","article_res/cover/91a5ee21dafecb914fabeb9430d46ec1.jpeg","Would Einstein lose his job - AI and Quantum Computing: A Glimpse into the Near Future","So Einstein's job is still safe.",{"id":136,"publish_date":137,"is_original":23,"collection":138,"cover_url":139,"cover_url_1_1":140,"title":141,"summary":142,"author":28},101,"2024-12-14","#Nvidia #AI 3D Generator","article_res/cover/693e07c85980c5c0c8fde3f037733f23.jpeg","article_res/cover/9ea8edff2d5d303ff3fffff3f6f9c3d9.jpeg","NVIDIA's open-source 3D project LLaMA-Mesh","LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models",{"id":144,"publish_date":145,"is_original":23,"collection":146,"cover_url":147,"cover_url_1_1":148,"title":149,"summary":150,"author":28},131,"2024-11-10","#OpenAI","article_res/cover/87f8ed353ce39f31960e7cdfaf075a35.jpeg","article_res/cover/f597a63935f5cd32e484b4aadd6019e8.jpeg","ChatGPT has launched the Search function","Get fast, timely answers with links to relevant web sources.",{"big":152,"small":214},[153,181],{"title":154,"list":155},"AGENT",[156,157,165,173],{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":158,"publish_date":159,"is_original":23,"collection":160,"cover_url":161,"cover_url_1_1":162,"title":163,"summary":164,"author":28},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":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},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",{"id":174,"publish_date":175,"is_original":23,"collection":176,"cover_url":177,"cover_url_1_1":178,"title":179,"summary":180,"author":28},616,"2025-03-29","#MAS #AI Agent #AI Coder #MetaGPT #MGX","article_res/cover/9dcd702ad2035902e5e77967c34a1f1e.jpeg","article_res/cover/0a97fc4a922753c8f46ff38792020df8.jpeg","MGX - An automated website-building platform composed of multiple AI Agents","Your 24/7 AI Team | Dream, Chat, Create.",{"title":182,"list":183},"OPENAI",[184,191,199,206],{"id":185,"publish_date":167,"is_original":23,"collection":186,"cover_url":187,"cover_url_1_1":188,"title":189,"summary":190,"author":28},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":192,"publish_date":193,"is_original":4,"collection":194,"cover_url":195,"cover_url_1_1":196,"title":197,"summary":198,"author":28},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":200,"publish_date":201,"is_original":4,"collection":146,"cover_url":202,"cover_url_1_1":203,"title":204,"summary":205,"author":28},417,"2023-08-24","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.",{"id":207,"publish_date":208,"is_original":4,"collection":209,"cover_url":210,"cover_url_1_1":211,"title":212,"summary":213,"author":28},407,"2023-09-22","#OpenAI #AI Image Generator","article_res/cover/c59005e903d35cfc32346e2756e2728a.jpeg","article_res/cover/ba011d265e6d84b5c8cb6fd6b757b6cc.jpeg","Dall-E 3","DALL·E 3 understands significantly more nuance and detail, allowing you to easily translate your ideas into images.",[215,221,241],{"title":10,"list":216},[217,218,219,220],{"id":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},{"id":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"title":222,"list":223},"GOOGLE",[224,225,226,234],{"id":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"id":227,"publish_date":228,"is_original":23,"collection":229,"cover_url":230,"cover_url_1_1":231,"title":232,"summary":233,"author":28},615,"2025-03-30","#AI Researcher #AI Science #HKU #Google #AI Agent","article_res/cover/21fadf906067714bb0db31ae13a77c15.jpeg","article_res/cover/2697999a72bd26b22e85f0e92936d3ed.jpeg","AI-Researcher: LLM-driven全自动 scientific research assistant","AI-Researcher: Fully-Automated Scientific Discovery with LLM Agents  \nOpen-Sourced Alternative to Google AI Co-Scientist",{"id":235,"publish_date":236,"is_original":23,"collection":73,"cover_url":237,"cover_url_1_1":238,"title":239,"summary":240,"author":28},463,"2023-05-09","article_res/cover/89800f207723acdb55fc53bf999ebdc9.jpeg","article_res/cover/5764f369b4accd8f83e94aa4c077a175.jpeg","The Smallville sandbox world - A town with 25 virtual residents","Believable proxies of human behavior can empower interactive apps: Immersive environment, Rehearsal space, Prototyping tool",{"title":242,"list":243},"NVIDIA",[],true,{"code":4,"msg":5,"data":246},{"id":247,"publish_date":248,"is_original":23,"collection":249,"articles_id":250,"cover_url":251,"cover_url_1_1":252,"title":253,"summary":254,"author":28,"content":255,"popular":256,"list":323,"category":380,"tag":381},284,"2024-05-04","#AI Index Report 2024","ONKH-8b5xglXF6MZvvbMvQ","article_res/cover/cba905132168c996108de5af21120030.jpeg","article_res/cover/056d14bc0f7a1f12715fdd4ef9f261dc.jpeg","\"The 2024 Artificial Intelligence Index Report\" - 2.10 Reinforcement Learning","RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","\u003Cdiv class=\"rich_media_content js_underline_content\n                       autoTypeSetting24psection\n            \" id=\"js_content\">\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Chapter 2.10 of the report discusses three reinforcement learning methods: RLHF, RLAIF, and DPO.\u003C/p>\u003Ch3 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 20px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>RLHF\u003C/h3>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>RLHF (Reinforcement Learning with Human Feedback) is a well-known reinforcement learning technique that optimizes model performance by combining the output of machine learning models with feedback provided by humans. It has been widely applied in several renowned models such as GPT-4, Llama2, Claude 2, and Gemini; however, not all models use RLHF. For example, Mistral 7B does not adopt this method.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100004243\" data-ratio=\"0.9352941176470588\" data-s=\"300,640\" data-type=\"png\" data-w=\"1020\" style=\"\" src=\"./assets/17423805924740.6594266143958609.png\">\u003C/p>\u003Ch3 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 20px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>DPO\u003C/h3>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Regarding DPO (Direct Preference Optimization), we have already discussed it in detail in our previous articles. Please refer to the previous content -\u003C/p>\u003Ch3 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 20px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>RLAIF\u003C/h3>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Today, we will focus on introducing RLAIF — Reinforcement Learning with Artificial Intelligence Feedback. This is a newer approach that trains and optimizes models using feedback generated by AI itself, rather than entirely relying on human feedback. This method can reduce dependence on large-scale manual annotations while maintaining data quality, thereby improving learning efficiency.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100004246\" data-ratio=\"0.549074074074074\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423805924820.3400366789349667.png\">\u003C/p>\u003Cp>\u003Cbr>\u003C/p>\u003Ch3 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 20px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>More details:\u003C/h3>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Although RLHF (Reinforcement Learning with Human Feedback) has long been considered the gold standard for AI model calibration, its reliance on large amounts of human feedback data often becomes a limiting factor in terms of time and labor. As an alternative, a recent Google Research study proposed a method of using preferences from large language models for reinforcement learning — RLAIF (Reinforcement Learning with AI Feedback), aiming to calibrate other AI models toward human preferences.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100004247\" data-ratio=\"0.8672199170124482\" data-s=\"300,640\" data-type=\"jpeg\" data-w=\"241\" style=\"\" src=\"./assets/17423805924750.09369583618916422.jpeg\">\u003C/p>\u003Ch3 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 20px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>RLAIF vs. RLHF: Which is more efficient?\u003C/h3>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>The study compared the performance of RLAIF and RLHF in summarization and helpfulness tasks, finding that both are preferred over supervised fine-tuning (SFT). Statistically, there was no significant difference between the advantages of RLHF and RLAIF (see the figure below).\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100004244\" data-ratio=\"0.974308300395257\" data-s=\"300,640\" data-type=\"png\" data-w=\"1012\" style=\"\" src=\"./assets/17423805924750.936086215339591.png\">\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Notably, in the task of generating harmless dialogues aimed at producing the least harmful outputs, the effectiveness of RLAIF (88%) exceeded that of RLHF (76%) (see the figure below). This suggests that RLAIF may be a more resource-efficient and cost-effective method for calibrating AI models.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100004245\" data-ratio=\"0.9603960396039604\" data-s=\"300,640\" data-type=\"png\" data-w=\"1010\" style=\"\" src=\"./assets/17423805925170.4758939676912737.png\">\u003C/p>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",[257,266,275,283,291,299,307,315],{"id":258,"title_md5":259,"publish_date":260,"author_md5":261,"is_original":23,"collection":262,"summary_md5":263,"cover_url":264,"cover_url_1_1":265},4,"2a89ef823c4c1ea3a34a3dae0ff1419b","2025-03-16","bc27fa490c4d0d525bac812fc0793534","#VLM-R1 #Large Vision-Language Model #GRPO","d3daa0f413010e2b97a2dc97ff1317dc","article_res/cover/262d831f5b3b6f3958d243586327d2f2.jpeg","article_res/cover/0b297b83de0f7b4572aac35ac4f14507.jpeg",{"id":267,"title_md5":268,"publish_date":269,"author_md5":270,"is_original":4,"collection":271,"summary_md5":272,"cover_url":273,"cover_url_1_1":274},587,"ad8ecf48251433b17d60bb444fdb0684","2022-03-30","4f827bb0e8f01a866d164bd7eaf8b2a4","#Psychology","32bf145ae17ff55a1390c4f00222e25c","article_res/cover/159eaa627dae6a3aa2f0138aaa3079e9.jpeg","article_res/cover/3247d6e9cc489a24c763f0b261a4089a.jpeg",{"id":276,"title_md5":277,"publish_date":278,"author_md5":261,"is_original":23,"collection":279,"summary_md5":280,"cover_url":281,"cover_url_1_1":282},267,"361d581d771bb3317343187763be8e8b","2024-05-23","#ByteDance #AI Story","76b25af0cbe58dc269896bc8f2e5d1f7","article_res/cover/a9f3801b9c8a9e279850484885da5cf7.jpeg","article_res/cover/3f582251b68e2c3a25f1f4366e72ccfa.jpeg",{"id":284,"title_md5":285,"publish_date":286,"author_md5":287,"is_original":4,"collection":5,"summary_md5":288,"cover_url":289,"cover_url_1_1":290},554,"5c5ca223c42ba689bf3130ab1b859e9e","2022-05-02","70997a2931a60561e615f5171df5f9a5","20d4fd7a8a95643eafcb19d8476fa89e","article_res/cover/5e0e1b6c5a43cc8e35ce6e45e8250f50.jpeg","article_res/cover/fbbab82bf840d89770767f59c7dd43b7.jpeg",{"id":292,"title_md5":293,"publish_date":294,"author_md5":261,"is_original":23,"collection":295,"summary_md5":296,"cover_url":297,"cover_url_1_1":298},11,"4fbd09f74c8435e264fd7d026a9bb163","2025-03-10","#AI Agents #AI Coder #Operator #OpenAI #Replit","892c7a882780396423fd6b01d8713bdd","article_res/cover/7158ed3b6308013fdcd6191afd7b33ee.jpeg","article_res/cover/7a04464dca913878218970fa718957a5.jpeg",{"id":300,"title_md5":301,"publish_date":302,"author_md5":303,"is_original":4,"collection":5,"summary_md5":304,"cover_url":305,"cover_url_1_1":306},577,"e049d7a99f585f82de08c36d769611a0","2022-04-09","46d4befbaca33274c83a26b5fc7c9d12","e0a47cf523942d77b05e0b98f3b5a980","article_res/cover/4482e63f9a8a649b2f272f91f453b607.jpeg","article_res/cover/764f78c1bb5669685f803ef084ad0725.jpeg",{"id":308,"title_md5":309,"publish_date":310,"author_md5":261,"is_original":23,"collection":311,"summary_md5":312,"cover_url":313,"cover_url_1_1":314},453,"c15cd6a35923a6347b652fc85e515cf4","2023-05-24","#AI Audio Generator","f829be1e3a46f19275b2ad53ce960b35","article_res/cover/9f9d88dde4a788562db422dbf0a2872d.jpeg","article_res/cover/29ac820986dde6a7bff6e359574cef18.jpeg",{"id":316,"title_md5":317,"publish_date":318,"author_md5":261,"is_original":23,"collection":319,"summary_md5":320,"cover_url":321,"cover_url_1_1":322},455,"edd76001b3dff74b89da9cb08bf965e6","2023-05-18","#AI 3D Generator","6bf80ad0508101e94f2b7d8778a11f0b","article_res/cover/e3196d033c293aba1a85401ff4e0156a.jpeg","article_res/cover/520d7522a47d2d1153458ef7fa8118a0.jpeg",{"related":324,"small":365},[325,333,341,349,358],{"id":326,"publish_date":327,"is_original":4,"collection":5,"cover_url":328,"cover_url_1_1":329,"title":330,"summary":331,"author":332},598,"2022-03-19","article_res/cover/c0b3c15d1af9917e4888e30976e49606.jpeg","article_res/cover/9812ac9f3a9898718353dda47d933a29.jpeg","Michael Saylor on Context Livestream","Stocks valued on expected cash flows only hold value if those cash flows grow faster than the rate of monetary expansion.","Translation",{"id":334,"publish_date":335,"is_original":23,"collection":336,"cover_url":337,"cover_url_1_1":338,"title":339,"summary":340,"author":28},37,"2025-02-16","#Deep Dive into LLMs #Andrej Karpathy #LLM #Self","article_res/cover/9af22e1c164374b6cda23c7c0fc490e0.jpeg","article_res/cover/004d36f7eed707f381f30466314ab99d.jpeg","\"Self-awareness\" of LLM - Andrej Karpathy's in-depth explanation of LLM (Part 5)","Knowledge of self",{"id":342,"publish_date":343,"is_original":4,"collection":344,"cover_url":345,"cover_url_1_1":346,"title":347,"summary":348,"author":28},401,"2023-10-01","#Object Detection #AI Agent #Langchain","article_res/cover/2dce58eb9163407c184896e9f1ce75b4.jpeg","article_res/cover/8c8d5cac60fb88a5d02561dc86bb97a0.jpeg","Use Eden AI tools in Langchain Agent","Eden AI | AI made easy for all Product Builders",{"id":350,"publish_date":351,"is_original":4,"collection":352,"cover_url":353,"cover_url_1_1":354,"title":355,"summary":356,"author":357},166,"2024-09-28","#History of Intelligence #Neuroscience","article_res/cover/f8369fb63aabb4d9022b46f4e4786223.jpeg","article_res/cover/a89cf18d49193ae495dffd23bd3623e7.jpeg","【A Brief History of Intelligence】3. Reinforcing (Vertebrates)","Curiosity and reinforcement learning coevolved because curiosity is a requirement for reinforcement learning to work.","Notes on \"A Brief History of Intelligence\"",{"id":359,"publish_date":360,"is_original":4,"collection":146,"cover_url":361,"cover_url_1_1":362,"title":363,"summary":364,"author":28},382,"2023-11-10","article_res/cover/f3614fc55023f05303030c499936e0f3.jpeg","article_res/cover/63d26a9fb3be7c181f32c9c9f630fd4b.jpeg","GPTs Experience (Upper Chapter)","You can now create custom versions of ChatGPT that combine instructions, extra knowledge, and any combination of skills.",[366,372,378],{"title":10,"list":367},[368,369,370,371],{"id":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},{"id":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"title":222,"list":373},[374,375,376,377],{"id":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"id":227,"publish_date":228,"is_original":23,"collection":229,"cover_url":230,"cover_url_1_1":231,"title":232,"summary":233,"author":28},{"id":235,"publish_date":236,"is_original":23,"collection":73,"cover_url":237,"cover_url_1_1":238,"title":239,"summary":240,"author":28},{"title":242,"list":379},[],[8,9,10],[8,12,13,14,9,10,15,16,17,18],["Reactive",245],1754646419300]