在被视为未来经济主导领域的人工智能方面，中国已取得多项成功。过去十年间，全球70%的生成式人 工智能相关专利来自中国，据报道全球47%的顶尖人工智能人才源自中国。 在韩国，我们有许多研究美国和日本的专家，但深入研究中国的却少得多——考虑到中国对韩国未来的 重要性，这一现象令人惊讶。当然，理解任何国家都非易事，尤其是中国这样幅员辽阔、情况复杂的国 家。然而，分析中国科技崛起的成因及影响，是韩国为未来做准备的关键。毕竟，中韩两国注定要在高 端制造业领域展开全球竞争。 来源：环球时报 韩国《中央日报》6月27日文章，原题：我们对中国到底了解多少？ 全球范围内，对中国科技能力的认 知正在经历根本性转变，越来越多人意识到中国已崛起为世界级技术和工业产品的生产国。这一认知转 变的主要触发点是近期的"深度求索（DeepSeek）震撼"。尽管受美国出口管制影响无法获取尖端半导 体，这家中国小型人工智能研究公司仍成功开发出可与OpenAI等科技巨头媲美的大型语言模型。 这一成功并非孤例。甚至在DeepSeek取得突破前，已有大量证据显示中国科技水平已达全球领先标 准。例如在无人机领域，中国企业大疆占据全球70%以上市场份额；中 ...

Core Viewpoint - The release of DeepSeek-R2 has been delayed due to CEO Liang Wenfeng's dissatisfaction with its performance and a shortage of Nvidia H20 chips, which are critical for its development [1][2][4]. Group 1: Development Timeline - The anticipation for R2 began after the release of the DeepSeek-V3 model in December last year, which was considered a benchmark for cost-performance [5]. - Initial expectations suggested that R2 would be launched in April, following the upgrade of V3 on March 24 [11]. - Despite the release of a paper on inference scaling in April, there has been no official update on R2's launch [12][16]. Group 2: Technical Specifications - R1's training utilized 30,000 H20 chips, 10,000 H800 chips, and 10,000 H100 chips, indicating the significant computational resources required for R2 [3]. - Leaked parameters for R2 suggested it would have 1.2 trillion parameters and utilize 5.2 petabytes of training data, raising questions about its hardware requirements [17]. Group 3: Community Reactions - Following the news of the delay, community responses varied, with some expressing belief that the delay would be worthwhile, while others speculated that R2 might wait for the release of V4 [26][28].

AI Reasoning Models - AI reasoning models were expected to be the industry's next major advancement, leading to smarter systems and potentially superintelligence [1] - Major AI players like OpenAI, Anthropic, Alphabet, and DeepSeek have released models with reasoning capabilities [1] - These reasoning models aim to solve complex problems by breaking them down into logical steps [1] Research Findings - Recent research is questioning the effectiveness of these AI reasoning models [1]

Germany tells Apple, Google to remove DeepSeek from the country's app stores | TechCrunch https://t.co/8T5xFn6Icc ...

In this photo illustration, the DeepSeek logo is seen displayed on a smartphone screen and in the background, the flag of the European Union.One of Germany's data protection watchdogs on Friday said DeepSeek's app illegally sends user data to China and asked Google and Apple to consider blocking the artificial intelligence service.Berlin's data protection commissioner Meike Kamp said in a statement that DeepSeek's transfer of German user data to China is "unlawful." There is not a readily available way to g ...

China Investors Ready Capital to Hunt Next DeepSeek https://t.co/oeK73fSmZy ...

一水 发自 凹非寺 量子位 | 公众号 QbitAI 全网翘首以盼的 DeepSeek-R2 ，再次被曝推迟！ 据The Information报道，由于DeepSeek CEO梁文锋始终对R2的表现不满意，因此R2迟迟未能发布。 此外，他们还援引两位国内知情人士的消息称，R2研发进程缓慢可能是由于 缺少英伟达H20芯片 。 要知道R1的训练总计耗费了3万块H20 （国内特供版） 、1万块H800和1万块H100。 所以在H20吃紧的情况下，预计耗费更多算力资源的R2难免受到波及。 事实上，这不是R2第一次被曝项目延期了，最早能追溯到今年4月—— 一览R2"难产"始末 仔细一梳理，原来人们对R2的期待， 早在V3新版本出来后就开始了 。 去年12月底，DeepSeek发布了至今被视为"性价比代表"的DeepSeek-V3模型。到了今年3月24日，官方发布公告称对V3进行了一次升级， 新版本代号为V3-0324。 虽然官方轻描淡写只说是"小版本升级"，但很多人实测下来可一点也不小。 于是人们开始推测，在V3-0324已经取得明显进步的情况下，是不是可以用它来训练R2模型。 这里需要补充一下，DeepSeek主打 ...

Core Viewpoint - The implementation of the Private Economy Promotion Law provides a legal foundation for the sustainable and healthy development of private enterprises in China, instilling confidence in companies like Hainan Huayan [1][2]. Group 1: Legal Framework and Support - The Private Economy Promotion Law, effective from May 20, 2025, is the first fundamental law specifically aimed at promoting the development of the private economy in China [1]. - The law establishes a principle of "equal participation," which is crucial for innovative private enterprises seeking legal protection [1][2]. - It introduces a nationwide negative list system for market access, allowing various economic organizations, including private enterprises, to enter fields outside the list on an equal legal basis [3]. Group 2: Challenges and Opportunities - Despite facing challenges such as trade barriers and financing difficulties, private high-tech enterprises like Huawei and Yushutech demonstrate resilience and vitality through innovation [2]. - The law addresses issues such as market entry barriers, financing difficulties, and disadvantages in participating in research projects, which have historically hindered the growth of private enterprises [2][3]. Group 3: Financial Support and Innovation - The law mandates financial institutions to develop financial products tailored to the characteristics of private enterprises, enhancing credit supply and improving access to financing [4]. - It emphasizes the importance of intellectual property pledge financing, allowing private enterprises to secure funding for research and innovation [4]. - Hainan Huayan has successfully launched innovative products, such as collagen peptides, which have significantly increased revenue, showcasing the potential for growth through innovation [3][4]. Group 4: Market Dynamics and Competitive Strategies - The concept of "involution" in the market is addressed, with the company advocating for healthy competition that stimulates market vitality rather than destructive price wars [5]. - Hainan Huayan is exploring new applications for its products, expanding beyond traditional markets to include sports nutrition and health products for the elderly, thereby creating new market opportunities [5]. - The law's implementation is seen as a catalyst for private enterprises to leverage technological innovation and a legal business environment to ascend the value chain [5].

Tons of AI news. Let's get right into it. Deepseek R2 has been delayed according to the information. And the cause, US export controls. I didn't think those were actually going to work, but apparently maybe they are. And there are really two elements to this delay. First, the CEO of Deepseek isn't happy with the performance of Deepseek R2. And number two, even if it were good, they wouldn't have enough GPUs to run it. This is due to a shortage of Nvidia server chips in the country. According to employees of ...

Core Insights - The founder of Changba, Chen Hua, expresses anxiety about the upcoming opportunities in AI applications, likening the current situation to the pre-explosion phase of mobile internet around 2011 [2][3] - Chen believes that the AI wave represents a rewriting of the script compared to the mobile internet era, with distinct differences in commercialization paths and driving factors [3][4] Group 1: Historical Context and Development - Changba was founded in 2011 and launched its app in May 2012, quickly becoming a leader in mobile karaoke [2] - The company has evolved through various stages, including significant product launches and brand upgrades, with a new AI ToC app expected in 2025 [2] Group 2: Comparison of AI and Mobile Internet - Both AI and mobile internet share similar industry development cycles, with significant breakthroughs occurring years after initial technology releases [3][4] - The commercialization paths differ: mobile internet saw a To C explosion first, while AI applications are primarily To B at this stage [4][5] Group 3: Driving Factors and Commercialization - The mobile internet was driven by hardware revolutions, while AI is propelled by breakthroughs in underlying technologies [5][6] - AI applications focus on efficiency and cost-saving for businesses, contrasting with the user-scale monetization seen in mobile internet [7][8] Group 4: Competitive Landscape - The competitive landscape for mobile internet allowed early startups to create platforms, whereas AI applications face a more closed ecosystem dominated by large companies [9][10] - Despite challenges, Chen sees promising opportunities in To B efficiency tools and high-frequency To C tools in vertical fields [11][12] Group 5: Future Opportunities and Challenges - Chen emphasizes the importance of user feedback within two weeks of product launch as a critical measure of success [13][75] - The AI application landscape is still maturing, with many startups struggling to find viable paths due to competition and market saturation [14][36] Group 6: Investment and Market Dynamics - The investment landscape for AI applications is shifting, with a preference for dollar funds over RMB funds due to the latter's complexity [79] - The government is more focused on strategic investments in foundational technologies rather than direct AI application ventures [80]