У нас вы можете посмотреть бесплатно State of the AI World for Developers или скачать в максимальном доступном качестве, видео которое было загружено на ютуб. Для загрузки выберите вариант из формы ниже:
Если кнопки скачивания не
загрузились
НАЖМИТЕ ЗДЕСЬ или обновите страницу
Если возникают проблемы со скачиванием видео, пожалуйста напишите в поддержку по адресу внизу
страницы.
Спасибо за использование сервиса ClipSaver.ru
In this recorded Live! 360 session, Brian Randell breaks down the fast-moving AI landscape—from foundation models and multimodal systems to coding assistants, agent workflows, and on-device LLMs. You’ll see how AI is reshaping developer tools, how to choose the right models for your apps, what patterns actually work in production, and where agents and reasoning models are heading next. Brian demos real-world AI coding workflows in Visual Studio Code, GitHub Copilot, Model Context Protocol (MCP) integrations, local LLMs, and multimodal prompting—all while grounding everything in practical guidance about safety, cost, performance, and long-term strategy. 🔑 What You’ll Learn • The rapid evolution of AI systems: LLMs, diffusion models & multimodal reasoning • How to choose between frontier models, open models, and task-specific models • Why developer tools are becoming AI-first (VS Code, Visual Studio 2026, CLIs, agents) • How Model Context Protocol (MCP) gives AI tools domain-specific knowledge and context • How GitHub Copilot modes work: Ask, Edit, Plan & Agent • Running AI locally with Llama, Ollama, LM Studio & open-source UIs • Retrieval Augmented Generation (RAG) & practical patterns for AI-powered apps • Cost, performance, privacy & responsible AI considerations • What’s coming next with autonomous agents and cross-model reasoning ⏱️ Chapters 00:00 The AI landscape 11:00 Evolution of LLMs, diffusion models & multimodal systems 15:06 Major players and models 16:07 Hugging Face, an open market for AI models 17:40 Specialized models & running AI at the edge 21:10 Evolution of deep learning 22:35 Running AI locally: Ollama 27:30 Retrieval augmented generation (RAG): why good data matters more than models 32:14 Model Context Protocol (MCP) & tool integrations 43:45 GitHub Copilot Agent & other coding assistants 52:02 API choices: foundation, specialized & application-level APIs 53:20 Designing AI-enabled applications & UX patterns 58:00 Prompt design: system vs. user messages 59:37 Best practices: Cost, performance, monitoring, continuous improvement, filtering 1:05:25 Ethics, safety & responsible AI wrap-up 🔗 Links • Explore more Live!360 sessions: https://aka.ms/L360Orlando25 • Join us at upcoming VS Live! events: https://aka.ms/VSLiveEvents 👤 Speaker: Brian Randell #visualstudio #vscode #githubcopilot #ai