Hackathon Overview - CoinGecko is hosting an MCP Hackathon focused on building with crypto price data and AI [1] - The hackathon encourages participation from builders, researchers, and tinkerers [1] Prizes and Incentives - The hackathon offers prizes worth up to $13,000 [1] - Over $1,300 in prizes are specifically allocated for projects utilizing CoinGecko's crypto price data in AI and LLMs [1] Participation Details - Participants are invited to BuildwithCoinGecko and AI [1] - Interested individuals can find participation details at the provided URL [1]

Key Features - MCP-use 简化了 LLMs 连接到 MCP 服务器和构建本地 MCP 客户端的过程 [1] - 该工具与 Ollama 和 LangChain 兼容 [2] - 支持异步流式传输 Agent 的输出 [2] - 内置调试模式 [2] - 可以限制 MCP 工具的使用 [2]

Financial Data and Key Metrics Changes - Booking Holdings reported a strong quarter with adjusted EBITDA increasing by 28% year over year, driven by revenue outperformance and disciplined expense management [3][32] - Room nights reached 309 million, an 8% year over year increase, with gross bookings up 13% and revenue up 16%, both exceeding prior expectations [5][29] - Adjusted earnings per share grew 32% year over year, benefiting from a 5% lower average share count [32] Business Line Data and Key Metrics Changes - Alternative accommodations room nights grew by 10%, outpacing the core hotel business, with total listings reaching 8.4 million, an 8% increase year over year [8][25] - The Genius loyalty program saw over 30% of active travelers in higher tiers, contributing to a mid-50% share of total room nights booked [9][27] - Non-accommodation verticals showed strong growth, with flight tickets booked increasing by 44% and attractions ticket growth more than doubling year over year [12][27] Market Data and Key Metrics Changes - Asia experienced low double-digit room night growth, while the U.S. remained the slowest growing region, though growth improved slightly from the first quarter [10][22] - Europe saw high single-digit growth, and the Rest of World region also experienced high single-digit growth [22] - The U.S. market showed lower average daily rates (ADRs) and shorter lengths of stay, indicating cautious consumer spending [23] Company Strategy and Development Direction - The company is focused on expanding alternative accommodations, enhancing the Genius loyalty program, and developing AI capabilities to improve the travel experience [7][12] - The connected trip vision aims to provide a more personalized travel experience by integrating various travel services [11][82] - The company is investing in technology and partnerships to leverage AI for better service and operational efficiency [16][17] Management's Comments on Operating Environment and Future Outlook - Management remains optimistic about long-term growth in the travel industry despite geopolitical and macroeconomic uncertainties [18][39] - The company expects third quarter room night growth to moderate, with guidance reflecting a cautious outlook due to tougher year-over-year comparisons [35][72] - Full-year guidance has been increased, with expectations for low double-digit growth in gross bookings and revenue [39] Other Important Information - The company generated approximately $3.1 billion in free cash flow during the quarter, with an ending cash and investments balance of $18.2 billion [34] - The transformation program is expected to yield approximately $350 million in annual run rate savings [33] Q&A Session Questions and Answers Question: Can you provide details on the performance of different markets in Asia? - Management expressed satisfaction with overall performance in Asia, highlighting that while they do not compete strongly in China, inbound travel to China remains beneficial [45][46] Question: What is the potential impact of large language models (LLMs) on the business? - Management sees LLMs as an exciting opportunity for improved service and efficiency, although it is still early to quantify their impact [48][50] Question: What initiatives are being taken to boost growth in the U.S. market? - The company is focusing on small initiatives across product, supply, and marketing to gradually gain market share in the U.S. [58][60] Question: What are the key investments needed for scaling the Connected Trip? - Management emphasized the importance of expanding inventory across all travel verticals and leveraging data for personalized customer experiences [82][90]

Technology & Development - Open-source tools enable building production-grade LLM web apps rapidly [1] - Interactive apps are more suitable for users focused on results rather than code [1] Data Science & Machine Learning - Data scientists and machine learning engineers commonly use Jupyter for data exploration and model building [1] - Tutorials and insights on DS, ML, LLMs, and RAGs are shared regularly [1]

LLM技术解析 - KV caching in LLMs：LLM 中的 KV 缓存机制被清晰地解释，并附有可视化图表 [1]

Key Takeaways - The author encourages readers to reshare the content if they found it insightful [1] - The author shares tutorials and insights on DS (Data Science), ML (Machine Learning), LLMs (Large Language Models), and RAGs (Retrieval-Augmented Generation) daily [1] Focus Area - The content clearly explains KV caching in LLMs with visuals [1] Author Information - Avi Chawla's Twitter handle is @_avichawla [1]

Technology Overview - KV caching is utilized in Large Language Models (LLMs) to enhance performance [1] - The document provides a clear explanation of KV caching in LLMs with visuals [1]

General Overview - The document is a wrap-up and encourages sharing with the network [1] - It directs readers to Avi Chawla's profile for tutorials and insights on DS, ML, LLMs, and RAGs (Data Science, Machine Learning, Large Language Models, and Retrieval-Augmented Generation) [1] Focus Area - Avi Chawla's content includes explanations of Agentic AI systems [1]

Intuit's Use of LLMs in TurboTax - Intuit successfully processed 44 million tax returns for tax year 2023, aiming to provide users with high confidence in their tax filings and ensure they receive the best deductions [2] - Intuit's Geni experiences are built on GenOS, a proprietary generative OS platform designed to address the limitations of out-of-the-box tooling, especially concerning regulatory compliance, safety, and security in the tax domain [4][5] - Intuit uses Claude (Anthropic) for static queries related to tax refunds and OpenAI's GPT-4 for dynamic question answering, such as user-specific tax inquiries [9][10][12] - Intuit is one of the biggest users of Claude, with a multi-million dollar contract [9][10] Development and Evaluation - Intuit emphasizes a phased evaluation system, starting with manual evaluations by tax analysts and transitioning to automated evaluations using LLM as a judge [16][17] - Tax analysts also serve as prompt engineers, leveraging their expertise to ensure accurate evaluations and prompt design [16][17] - Key evaluation pillars include accuracy, relevancy, and coherence, with a strong focus on tax accuracy [20][24] - Intuit uses AWS Ground Truth for creating golden datasets for evaluations [22] Challenges and Learnings - LLM contracts are expensive, and long-term contracts are slightly cheaper but create vendor lock-in [25][26] - LLM models have higher latency compared to backend services (3-10 seconds), which can be exacerbated during peak tax season [27][28] - Intuit employs safety guardrails and ML models to prevent hallucination of numbers in LLM responses, ensuring data accuracy [40][41] - Graph RAG outperforms regular RAG in providing personalized and helpful answers to users [42][43]

Core Business & Services - Kalin builds custom solutions for clients, ranging from Fortune 500 companies to startups, focusing on app development and database migrations [1][2] - The company leverages generative AI to automate business functions, such as intelligent document processing for logistics management, achieving faster and better results than human annotators [20][21] - Kalin offers services ranging from chatbot and co-pilot development to AI agent creation, tailoring solutions to specific client needs [16] Technology & Architecture - The company utilizes multimodal search and semantic understanding of videos, employing models like Nova Pro and Titan v2 for indexing and searching video content [6][7] - Kalin uses various databases including Postgress, PG vector, and OpenSearch for vector search implementations [13] - The company builds AI systems on AWS, utilizing services like Bedrock and SageMaker, and custom silicon like Tranium and Inferentia for price performance improvements of approximately 60% over Nvidia GPUs [27] AI Development & Strategy - Prompt engineering has proven highly effective, sometimes negating the need for fine-tuning models [40] - Context management is crucial for differentiating applications, leveraging user data and history to make strategic inferences [33][34] - UX design is important for mitigating the slowness of inference, with techniques like caching and UI spinners improving user experience [36][37]