How We Scaled Kimi K2.5: Training Secrets of a 1 Trillion Parameter Model | GTC 2026 Keynote

This course focuses on learning several rules to improve speaking skills in important situations. Learners can master effective presentation methods for various contexts, such as interviews, thesis defenses, and oral exams.

This course enhances kanji learning through engaging video lectures covering kanji characters from Tobira lessons 6–10. Students will learn not only how to write kanji but also the fascinating stories behind each character.

This course is a seminar on the philosophical analysis of film art, focusing on how films create meaning through their formal structures. Learners will explore aesthetic issues surrounding appearance and reality, as well as the effects of film technology on communication and alienation.

This course covers matrix theory and linear algebra, emphasizing topics useful in other disciplines such as physics, economics, social sciences, natural sciences, and engineering. It parallels the combination of theory and applications in Professor Strang’s textbook Introduction to Linear Algebra.

This course provides a comprehensive introduction to systems engineering, focusing on both classical and modern approaches. Learners will explore key concepts such as stakeholder analysis, requirements definition, system architecture, and design optimization, applying these principles to real-world projects.

This course delves into the essential poker and mathematical concepts necessary for mastering Texas Hold'em at a professional level. Learners will explore strategies and theories that elevate their gameplay and decision-making skills.

This course focuses on the design and implementation of secure computer systems, exploring various threat models and security techniques. Learners will engage with topics such as operating system security, network protocols, and hardware security, drawing insights from recent research papers.

This course explores the principles of photoelectric conversion, focusing on charge excitation, conduction, separation, and collection. Learners will study both commercial and emerging photovoltaic technologies, alongside critical themes such as conversion efficiencies, loss mechanisms, and the societal impacts of solar energy.

This course immerses learners in an artificial intelligence programming contest where teams create virtual robots to compete in Battlecode, a real-time strategy game. Participants will enhance their programming skills through hands-on experience and optional lectures on relevant topics.

This course provides a fast-paced introduction to deep learning, focusing on practical model-building for complex problems involving unstructured data. Learners will explore deep neural networks, convolutional networks, transformers, and generative models like ChatGPT and Midjourney.

This course focuses on the modeling and analysis of random phenomena and processes, emphasizing statistical inference and probabilistic thinking. Learners will explore essential models and tools that combine mathematical rigor with conceptual understanding.

This course provides an introduction to the chemistry of biological, inorganic, and organic molecules. The emphasis is on basic principles of atomic and molecular electronic structure, thermodynamics, acid-base and redox equilibria, chemical kinetics, and catalysis.

This course explores the art of improvisation in both solo and ensemble settings, examining its connections to composition and performance through various musical traditions. Students will engage in hands-on music-making while discussing the aesthetics of improvisation and learning from guest artists across diverse genres.

This course provides a basic introduction to metric spaces, focusing on metrics, open and closed sets, and continuous functions. Learners will explore concepts such as completeness and compactness, laying a foundational understanding of mathematical analysis.

This course delves into the intricacies of high-level programming language implementation, focusing on compiler design and optimization techniques. Learners will engage in a hands-on project that involves building a compiler in Java® that generates MIPS executable machine code.

This course covers key topics in discrete applied mathematics, focusing on counting, generating functions, probability, and more. Learners will engage with both mathematical concepts and effective communication through writing assignments.

This course explores the mathematical concepts and techniques essential for the financial industry, blending theoretical mathematics with practical applications. Learners will study topics such as linear algebra, probability, statistics, and stochastic processes, guided by both MIT mathematicians and industry professionals.

This course explores the practical aspects of proving that certain problems cannot be solved efficiently, focusing on reductions and techniques for demonstrating computational hardness across various complexity classes. Learners will engage with interesting problems and develop a deeper understanding of algorithmic limitations.

This course covers the fundamentals of deep learning, including both theory and applications. Topics include neural net architectures (MLPs, CNNs, RNNs, graph nets, transformers), geometry and invariances in deep learning, backpropagation and automatic differentiation, learning theory and generalization in high dimensions, and applications to computer vision, natural language processing, and robotics.

This course delves into projection theory, exploring how a set behaves under various orthogonal projections. Learners will engage with both classical techniques and contemporary applications across multiple mathematical disciplines, including harmonic analysis and analytic number theory.

If you follow OpenClaw Parts 1 and 2, you eventually end up making a single agent do everything. As you do this, there comes a moment when prompts get tangled, memory gets mixed up, folders get messy, and you feel stuck, not knowing how to organize things anymore. This lecture is the "Introduction to Multi-Agents (Part 2.5)," designed to help you move one step further from that point. While maintaining a single bot, we will separate roles into two agents—planner and editor—and connect each agent to different workspaces and Telegram forum topics. You will personally build a structure where "different agents respond depending on which room you speak in." By following the hands-on practice, you will have the following in your environment: - A configuration file defining two agents: `content_planner` and `content_editor`, - A content folder structure where planning and drafting are separated, - A Telegram group chat where different agents are attached to specific forum topics, - And one actual draft of an Inflearn course introduction created through the collaboration of the two agents. In short, this is a practical class that helps you design the first step of upgrading your Telegram bot from a "single AI assistant" into a "small AI team with divided roles."

Complete everything from design to TDD and CI with Claude Code. Taking a single feature from one line of spec all the way to main merge.

An AI system that grades and reviews your code in just 5 seconds—imagination becomes reality. This course is an all-in-one project curriculum for creating a **'GitHub PR Auto-Analysis and Grading Bot'** using Spring AI. When a student submits an assignment (Pull Request), the server detects it, and the AI analyzes the code changes (Diff). The grading results are then stored in a database, feedback is automatically posted as a GitHub comment, and the student can check their results on a dedicated dashboard. From backend to AI integration and frontend (Vaadin), all with just Java! This is the ultimate introductory guide for any developer who wants to build their own AI service from A to Z.

Now, your AI is no longer in the cloud. It runs directly inside your laptop. Using LM Studio and Ollama, we will show you how to build a Private AI environment that runs entirely locally— from data processing and document analysis to code generation. Without security concerns, without costs, and even faster— Move beyond simply "using" AI and start "truly mastering" it.

Simple tutorials alone make it difficult to apply in practice. I will clearly pass on my professional know-how, covering complex state management and multi-agent design methods.

This is an advanced course focused on designing and implementing Multi-LLM architectures and orchestration-centered Agent systems (Main/Sub, Tool, Task Runtime, Agent Registry) by strategically combining GPT, Gemini, and LLaMA (local) based on Spring AI and Spring Boot. Moving beyond simple LLM calls, the curriculum covers the implementation of scalable, stable, and continuously improving AI systems. This involves applying Agentic Workflow Patterns (Chain, Parallel, Routing, Orchestrator–Workers, Evaluator–Optimizer) and Multi-Agent structures, separating execution layers like RAG and external APIs/DBs via Tool/ToolRegistry, and utilizing DAG engines, YAML declarative workflows, and Validated DSL (validation immediately after loading). Furthermore, the course includes Circuit Breakers, Reactive Streams, Redis monitoring, parallel processing, and iterative evaluation loops. It expands from Thymeleaf (SSR) exercises to decoupled Front-end/Back-end architectures using React and REST, while integrating tool and agent runtimes via MCP (Model Context Protocol) to build AI architecture design capabilities at a production-ready level. The ultimate goal is to evolve beyond being a simple AI user who merely integrates APIs and writes prompts, becoming a developer capable of designing AI systems—explaining and balancing Multi-LLM, agents, workflows, declarations, and validation within a single execution architecture.

AI writes on Slack and Notion for me? Work smarter with MCP, which goes beyond the limits of existing AI!

In the era of Agentic AI, where is AI development headed? Now, competitiveness lies not in using a single AI model well, but in the ability to select the right model for the task and connect AI Agents with development tools to solve real-world problems. We are releasing the presentation videos from the Qwen Conference 2026, a global AI conference hosted by Alibaba Cloud, for free. From the Qwen 2.5 Max announcement and the "Future of Reasoning" panel featuring NVIDIA and Fireworks AI, to multimodal models expanding into video and voice, and cases of AI Agents deployed in actual practice beyond mere demonstrations. Discover the direction of the Agent era as envisioned by a company that builds the entire stack—from models to infrastructure and applications.

Solve the point where 80% get stuck at makeathons. Complete Raspberry Pi · Computer Vision · LLM · 3D Design in 4 weeks! Achieve top rankings at makeathons with a demonstrable smart mirror PoC!

This course teaches you how to build AI agents from scratch to a production-ready level using OpenClaw. Beyond a simple introduction to features, you will master OpenAI, local LLMs, memory, sessions, Tools, and Skills in a single, cohesive workflow. Based on hands-on experience and know-how gained from developing AI and large-scale systems in Silicon Valley, the course explains architectures and operational methods applicable to real-world projects. By the end of the course, you will be able to design your own AI agents and implement automation by integrating them with various services. This is a practice-oriented course for those who want to go beyond just using AI and learn how to build and operate it themselves.

Build a Kiwoom Securities API-based automated stock trading system from scratch using the core features of Claude Code (MCP, Agents, Skills). It's perfectly fine for beginners. Get started with Claude Code right now!

Explore how LLM applications are shifting the development paradigm. Understand why LLMs are becoming a sustainable core technology through comparisons with existing technologies, and learn about the essential skills and mindset shifts required for developers. Gain insights from expert instructors to grasp the essence and future direction of LLM application development.

If you want to create your own AI service without coding, this course is the perfect solution. Using the Dify no-code platform, you can create high-quality AI apps with just your ideas. Instead of complex theory, it's structured around hands-on projects, allowing both AI beginners and working professionals to develop practical skills.

This is a tutorial-style Claude code development course that even beginners and those new to development can easily follow. Based on experience teaching offline classes for planners, designers, and non-developers, you can learn everything in a single flow—from basic examples not covered in books to intermediate development projects. Using Claude code, you will experience the step-by-step development process, starting from "Hello World" to a Lucky Draw app, a device-optimized cafe menu management web page integrated with Claude design and Excel data, and finally a SaaS web application that can be uploaded to databases and cloud services. Tutorials are provided in stages of theory, practice, and projects. Through six levels of hands-on exercises, you will master AI-collaborative development methodologies and experience the entire development cycle, including cloud deployment and operation.

Are you confused about which technology trends really matter among the flood of information? We've analyzed global reports from Gartner, Microsoft, and others to clearly explain 10 key technologies (multi-agent systems, physical AI, AI security, etc.) that will define 2026.

Innovation in Work Efficiency and Creativity – Agentic AI AI is now evolving beyond simple automation into a new stage where it can judge and execute on its own. Agentic AI is at the center of this change, serving as a core technology that helps businesses and organizations operate smarter. In this course, we have organized the content clearly and simply so you can understand how Agentic AI connects decision-making with execution and how it can be applied to practical work. Discover the essential knowledge for every professional preparing for the future right now.

We explore how to create an AI judge by combining knowledge graphs, reasoning systems, and various agent frameworks such as CrewAI, LangChain, and AutoGen, which enable the implementation of LLM-based multi-agent technology.

We're building an AI-powered video conferencing application with real-time AI agents, meeting summary features, and post-call functionality.

Develop various features using Spring WebFlux. This course will teach you WebFlux's essential concepts and practical implementation.

LLM: A pro quickly delivers core content, from essentials to practical tips!