Group 1 - The core point of the article is the rise of prompt engineering as a profession, highlighted by Riley Goodside's recent joining of Google DeepMind, marking a significant milestone in the field [1][6][12] - Riley Goodside became famous for earning over one million dollars annually by engaging with AI, particularly ChatGPT, which popularized the role of prompt engineers [1][6][12] - The profession of prompt engineering has gained legitimacy and importance over the past three years, contrary to initial skepticism about its sustainability [12][9] Group 2 - DeepMind's CEO Demis Hassabis and product head Logan Kilpatrick publicly welcomed Goodside, indicating the significance of his role within the company [2][3] - Goodside's background includes a degree in computer science from PennWest California and experience in data-related roles at various companies, showcasing his expertise in the field [8] - The article discusses the evolution of prompt engineering, emphasizing its role as a frontier in the development of large language models (LLMs) and the importance of effective prompt design [13][12] Group 3 - Goodside's notable contributions include designing advanced prompts that enhance the capabilities of AI models, demonstrating the potential of prompt engineering to unlock AI's full potential [19][10] - The article mentions the concept of "glitch tokens," which are specific tokens in AI models that can lead to unexpected outputs, showcasing the intricacies of prompt engineering [15][16] - Goodside's work is seen as a bridge between traditional programming and the new paradigm of interacting with AI through natural language prompts [9][13]

告诉你一个反直觉事实：对ChatGPT越凶，它回答的越准！来自宾夕法尼亚州立大学团队实证，4o在非常粗鲁情况下，拿下84.8%准确率。 别对你的ChatGPT太好了！ 一项来自PSU的最新研究，给所有人当头一棒——对LLM越粗鲁，它回答得就越给力。 诸如「请、谢谢」之类的客气话，以后不要再说了... 实验中，团队创建了一个包含50个基础问题的数据集，涵盖了数学、科学、历史领域，每个问题都被改写为五种礼貌等级—— 非常礼貌、礼貌、中性、粗鲁、非常粗鲁 论文地址：https://arxiv.org/pdf/2510.04950 最终，一共生成了250个prompt。ChatGPT-4o作为代表，参加了这场硬核测试。 结果令人大跌眼镜，总体上，不礼貌的提示「始终」比礼貌的提示，输出的结果表现更佳。 非常粗鲁：准确率84.8% 非常礼貌：准确率80.8% 这个观点早之前，有人很早就提出了，只不过这一次得到了研究实证。 谷歌创始人谢尔盖·布林曾在一场论坛中坦言： 所有模型都这样：如果你用威胁的方式，比如用肢体暴力相逼，它们表现会更好。 论文地址：https://arxiv.org/pdf/2402.14531 一年之后 ...

Core Insights - Anthropic has introduced new features in Claude that allow direct creation and editing of various mainstream office files, expanding AI's application in practical tasks [1] - The company emphasizes a shift in mindset towards designing tools for AI agents rather than traditional coding practices [3] - The effectiveness of AI agents is heavily reliant on the quality and design of the tools provided to them [8] Group 1: Tool Design Principles - The core principle is to design intuitive and user-friendly tools for uncertain, reasoning AI, rather than focusing solely on input-output like traditional programming [3] - Tools should be evaluated through real and complex tasks to ensure they meet practical needs and can identify genuine issues [4] - It is more beneficial to create integrated workflow tools that handle multi-step tasks rather than offering a collection of fragmented API functionalities [5] Group 2: Tool Evaluation and Improvement - Clear and precise descriptions of tools are crucial, as they are the only means for AI to understand their purpose [6] - The process of building and testing tool prototypes should involve comprehensive evaluations to measure performance and iteratively improve the tools [15][21] - Engaging AI agents in the evaluation process can help analyze results and refine tools effectively [33] Group 3: Effective Tool Usage - Selecting the right tools is essential; more tools do not necessarily lead to better outcomes, and tools should be designed with the unique capabilities of AI agents in mind [36] - Tools should be organized into namespaces to avoid confusion among AI agents when selecting which tool to use [39] - Returning meaningful context from tools is important, prioritizing high-information signals over technical identifiers [42] Group 4: Future Outlook - The approach to building effective tools for AI agents must evolve from predictable, deterministic patterns to non-deterministic models [54] - A systematic, evaluation-driven method for improving tools will ensure that as AI agents become more powerful, the tools they use will also evolve accordingly [54]

Core Insights - Companies with annual recurring revenue (ARR) exceeding $50 million are adopting strategies that contradict popular social media advice on prompt engineering [1][11] - The research indicates that traditional prompt engineering wisdom is often based on anecdotal evidence and small-scale tests, leading to ineffective practices [2] Misconceptions in Prompt Engineering - Misconception 1: Longer and more detailed prompts yield better results; research shows structured short prompts are more effective and cost-efficient, reducing API costs by 76% [3] - Misconception 2: More examples always help; recent studies indicate that excessive examples can confuse advanced models like GPT-4 and Claude [4][5] - Misconception 3: Perfect wording is crucial; the format and structure of prompts are more important than specific wording, with XML format outperforming natural language by 15% for certain models [6] - Misconception 4: Chain of thought prompts are universally applicable; they are effective for math and logic tasks but can hinder performance in data analysis, where table-based reasoning is more effective [7] - Misconception 5: Human experts create the best prompts; AI systems can optimize prompts more effectively and quickly than human experts, taking only 10 minutes compared to 20 hours for humans [8] - Misconception 6: Prompt engineering is a one-time task; ongoing optimization is essential as prompt performance declines over time, with systematic improvements potentially increasing performance by 156% over 12 months [9][10] Effective Strategies for High-Performing Companies - Successful companies focus on optimizing business metrics rather than model metrics, prioritizing user satisfaction and task completion rates [11] - They automate prompt optimization, employing systematic methods for continuous testing and improvement rather than manual iterations [11] - These companies emphasize structure, organization, and clarity over clever wording or lengthy examples [11] - They tailor techniques to specific task types, using appropriate methods like chain of thought for math and direct instructions for other applications [11][14] - They treat prompts as products, requiring ongoing maintenance and improvement based on real user data [11] Methodological Gap - The persistence of misconceptions stems from a fundamental methodological gap between academic research and industry practices, with academia relying on controlled experiments and industry often depending on intuition [12] - Understanding these research findings is crucial for anyone building AI capabilities, emphasizing structure over content and the importance of automated optimization [12][13] Competitive Advantage - Companies that base their prompt engineering on research rather than traditional views achieve significant competitive advantages, realizing higher performance at lower costs [17][18] - They can focus human expertise on high-value activities like defining goals and evaluating outcomes instead of manual prompt crafting [18] Questions for Teams - Teams should shift their focus from "How can we write better prompts?" to "How can we systematically optimize our AI interactions based on empirical evidence?" [19] - This perspective encourages data-driven approaches, enabling the development of scalable AI functionalities that deliver sustainable value [19]

Core Concept - The article emphasizes the evolution of prompt engineering into "context engineering," highlighting its importance in optimizing large language models (LLMs) for task execution [3][5][19]. Summary by Sections Definition and Importance - Context engineering is described as a critical process that involves adjusting the instructions and relevant background needed for LLMs to perform tasks effectively [3][5]. - The term "context engineering" is preferred as it encompasses the core tasks of prompt engineering while addressing its limitations [5][19]. Practical Application - A specific case study using n8n to develop an AI agent workflow illustrates the practical implementation of context engineering [6][7]. - The workflow includes designing management prompts, debugging instructions, and managing dynamic elements like user input and date/time [7][10]. Key Components of Context Engineering - Effective context engineering requires careful consideration of instructions, user inputs, and structured input/output formats to ensure clarity and efficiency [11][12]. - The article outlines the necessity of defining subtasks with specific parameters such as unique IDs, search queries, source types, and priority levels [12][13]. Tools and Techniques - The use of tools like n8n facilitates the integration of dynamic context, such as current date and time, which is crucial for time-sensitive queries [15][18]. - RAG (Retrieval-Augmented Generation) and memory mechanisms are discussed as methods to enhance workflow efficiency by caching user queries and results [16][17]. Challenges and Future Directions - The article notes that context engineering is complex and requires multiple iterations to refine the process [25][26]. - It anticipates that context engineering will evolve into a core skill for AI developers, with potential for automation in context handling [28][29][30].

Core Insights - The article emphasizes the emerging importance of communication skills in the context of AI, particularly the ability to translate AI insights into actionable human decisions, which is becoming a core competitive advantage [3][14][18] Group 1: Current Trends in AI and Workforce - Many professionals are focusing on learning prompt engineering and AI tool usage to adapt to workplace changes driven by AI [2][8] - A small group of specialists is positioning themselves in more valuable areas by learning how to make AI serve human needs rather than competing with it [3][9] Group 2: Challenges in AI Implementation - Despite the rapid advancements in AI, many AI-generated outputs are often ignored by teams due to a lack of understanding of how to bridge the gap between AI insights and human decision-making [5][6][11] - The current bottleneck lies in human comprehension, as many professionals are not effectively translating AI outputs into actionable insights [6][7] Group 3: The Role of the "Translation Layer" - The concept of a "translation layer" is introduced, which involves individuals who can convert AI's outputs into understandable and actionable human directives [9][10][14] - Companies need professionals who can explain AI recommendations to non-technical executives and help prioritize AI insights for actionable plans [16][17] Group 4: Strategies for Becoming a Key Translator - The article outlines three steps to become a key translator: recognizing the nature of the transformation, identifying gaps between AI outputs and human needs, and establishing oneself in the translator role [9][11][13] - Emphasizing the importance of simplifying complex AI insights and contextualizing them within the organization's culture and priorities is crucial for effective communication [13][14] Group 5: Future Outlook - As AI continues to evolve, the demand for professionals who can effectively interpret and implement AI insights will grow, making communication skills increasingly valuable [15][18] - The future will favor those who can bridge the gap between AI capabilities and human understanding, ensuring that AI serves as a tool for enhancing decision-making rather than a competitor [10][18]

Core Viewpoint - The article discusses the influential contributions of Andrej Karpathy in the AI field, particularly his role in coining significant terms and concepts that have shaped the industry, such as "hallucinations," "Software 2.0," "Software 3.0," "vibe coding," and "bacterial coding" [1][6][9]. Group 1: Naming and Concepts - Karpathy coined the term "hallucinations" to describe the limitations of neural networks, which generate meaningless content when faced with unfamiliar concepts [1][3]. - He is recognized as a master of naming in the AI community, having introduced terms like "Software 2.0" and "Software 3.0," which have gained traction over the years [6][9]. - The act of naming is emphasized as a foundational behavior in knowledge creation, serving as a stable target for global scientific focus [7]. Group 2: Software Evolution - "Software 1.0" refers to traditional programming where explicit instructions are written in languages like Python and C++ [12][14]. - "Software 2.0" represents a shift to neural networks, where developers train models using datasets instead of writing explicit rules [15]. - "Software 3.0" allows users to generate code through simple English prompts, making programming accessible to non-developers [16][17]. Group 3: Innovative Programming Approaches - "Vibe coding" encourages developers to immerse themselves in the development atmosphere, relying on LLMs to generate code based on verbal requests [22][24]. - "Bacterial coding" promotes writing modular, self-contained code that can be easily shared and reused, inspired by the adaptability of bacterial genomes [30][35]. - Karpathy suggests balancing the flexibility of bacterial coding with the structured approach of eukaryotic coding to support complex system development [38]. Group 4: Context Engineering - Context engineering has gained attention as a more comprehensive approach than prompt engineering, focusing on providing structured context for AI applications [43][44]. - The article highlights a shift towards optimizing documentation for AI readability, indicating a trend where 99.9% of content may be processed by AI in the future [45].

Core Insights - The article discusses the emerging field of Context Engineering, emphasizing the need for a systematic theoretical framework to complement practical experiences shared by Manus' team [1][2] - A comprehensive survey titled "A Survey of Context Engineering for Large Language Models" has been published, analyzing over 1400 research papers to establish a complete technical system for Context Engineering [1][2] Context Engineering Components - Context Engineering is built on three interrelated components: Information Retrieval and Generation, Information Processing, and Information Management, forming a complete framework for optimizing context in large models [2] - The first component, Context Retrieval and Generation, focuses on engineering methods to effectively acquire and construct context information for models, including practices like Prompt Engineering, external knowledge retrieval, and dynamic context assembly [2] Prompting Techniques - Prompting serves as the starting point for model interaction, where effective prompts can unlock deeper capabilities of the model [3] - Zero-shot prompting provides direct instructions relying on pre-trained knowledge, while few-shot prompting offers a few examples to guide the model in understanding task requirements [4] Advanced Reasoning Frameworks - For complex tasks, structured thinking is necessary, with Chain-of-Thought (CoT) prompting models to think step-by-step, significantly improving accuracy in complex tasks [5] - Tree-of-Thoughts (ToT) and Graph-of-Thoughts (GoT) further enhance reasoning by allowing exploration of multiple paths and dependencies, improving success rates in tasks requiring extensive exploration [5] Self-Refinement Mechanisms - Self-Refinement allows models to iteratively improve their outputs through self-feedback without requiring additional supervised training data [8][9] - Techniques like N-CRITICS and Agent-R enable models to evaluate and correct their reasoning paths in real-time, enhancing output quality [10][11] External Knowledge Retrieval - External knowledge retrieval, particularly through Retrieval-Augmented Generation (RAG), addresses the static nature of model knowledge by integrating dynamic information from external databases [12][13] - Advanced RAG architectures introduce adaptive retrieval mechanisms and hierarchical processing strategies to enhance information retrieval efficiency [14][15] Context Processing Challenges - Processing long contexts presents significant computational challenges due to the quadratic complexity of Transformer self-attention mechanisms [28] - Innovations like State Space Models and Linear Attention aim to reduce computational complexity, allowing models to handle longer sequences more efficiently [29][30] Context Management Strategies - Effective context management is crucial for organizing, storing, and utilizing information, addressing issues like context overflow and collapse [46][47] - Memory architectures inspired by operating systems and cognitive models are being developed to enhance the memory capabilities of language models [48][50] Tool-Integrated Reasoning - Tool-Integrated Reasoning transforms language models from passive text generators into active agents capable of interacting with the external world through function calling and integrated reasoning frameworks [91][92]

时令 发自 凹非寺 量子位 | 公众号 QbitAI 我每天都使用AI，我认为提示工程是一项高级认知技能。 说这话的，正是身价刚刚超过巴菲特的 黄仁勋 。 他还表示，人们对人工智能会消灭工作岗位的担忧被夸大了，但这并不意味着工作方式不会发生巨大变化。 他百分之百肯定，每个人的工作都会发生变化。 此言出自老黄在CNN（美国有线电视新闻网）的最新访谈。 此外，他还在访谈中提及了中国市场的重要性。 值得一提的是，黄仁勋在接受央视采访时宣布最新进展： 1、H20已被批准销往中国市场：这是个非常、非常好的消息； 2、将发布新显卡RTX Pro：这款显卡非常重要，专为计算机图形、数字孪生和AI设计。 通过大规模减少任务重塑工作 黄仁勋相信AI将重塑几乎所有工作岗位——不是通过大规模失业，而是通过大规模的任务削减和重构。 有些工作会消失，但也会创造出很多新的岗位。我希望，各行各业因人工智能带来的生产力提升，最终能够推动整个社会的发展。 我并不是让它替我思考，而是让它教我那些我还不了解的知识，或者帮助我解决那些我自己难以合理解决的问题。 他认为，向AI发出有效提示本身就是一项技能，既需要认知上的努力，也需要表达的清晰度。 作 ...

Core Viewpoint - The article discusses the emerging concept of "context engineering" in AI, suggesting it is a more accurate term than "prompt engineering" to describe the skills needed for effectively utilizing large language models (LLMs) [1][2]. Group 1: Importance of Context Engineering - Context engineering is essential for optimizing the performance of AI agents, as insufficient context can lead to inconsistent actions among sub-agents and hinder the ability to follow instructions accurately [4][5]. - The performance of LLMs can decline if the context is too long or contains irrelevant information, which can also increase costs and delays [4][5]. - Instruction adherence is crucial for agents, with top models showing a significant drop in accuracy during multi-turn conversations, highlighting the need for optimized context length and accuracy [4][5]. Group 2: Strategies for Optimizing Context Engineering - Context engineering encompasses three common strategies: compression, persistence, and isolation [5][6]. - Compression aims to retain only the most valuable tokens in each interaction, with methods like context summarization being critical [6][7]. - Persistence involves creating systems for storing, saving, and retrieving context over time, considering storage methods, saving strategies, and retrieval processes [9][10]. - Isolation focuses on managing context across different agents or environments, utilizing structured runtime states to control what LLMs see in each interaction [16][18]. Group 3: Practical Experiences and Recommendations - The article emphasizes the importance of building robust context management systems for AI agents, balancing performance, cost, and accuracy [24]. - It suggests that memory systems should be simple and track specific agent preferences over time, while also considering parallelizable tasks for multi-agent architectures [26]. - The need for a token tracking mechanism is highlighted as foundational for any context engineering work [23].