Developers May Stop Depending on Libraries

In this episode of Agentic Conversations, we're joined by Shaun Smith, software engineer, open source advocate, and contributor at Hugging Face, to explore how AI coding has changed almost overnight.We dive into reinforcement learning, MCP (Model Context Protocol), Fast Agent, Claude Code, open source AI, and why today's language models have become so capable that many traditional software libraries are becoming "liquefied." Shaun explains how reinforcement learning unlocked long-running autonomous agents, why ideas are becoming more valuable than code, and how developers should think about building software in an era where AI can generate entire applications.Along the way, we discuss Hugging Face's MCP server, Fast Agent, AI-powered developer tools, multimodal applications, MCP Apps, context windows, coding assistants, Rust, Python, TypeScript, open-weight models, software architecture, and what the future of programming looks like when humans increasingly focus on design instead of implementation.Shaun Smith: https://www.linkedin.com/in/smithshaunDemetrios: https://www.linkedin.com/in/dpbrinkmHugging Face: https://huggingface.coTimestamps:00:00 Introduction01:56 The State of Open Source AI05:18 Reinforcement Learning Changed Everything07:50 Fast Agent Explained10:18 Fast Agent as an MCP Reference Platform12:20 Building Smarter AI Tools at Hugging Face15:17 Natural Language Search Instead of APIs17:46 Why MCP Apps Matter20:06 The Evolution of MCP Apps23:05 Building AI-Native User Interfaces26:12 Context Is the New Programming Language28:00 The End of Code Libraries29:50 Why Developers Aren't Writing Code31:25 AI Changes Software Engineering33:05 The Future of Open Source AI35:43 Claude Skills That Save Hours38:02 Training Models with AI39:05 Building Your Own AI Tools40:50 MCP for Consumers, Enterprises, and Developers43:42 Why Shell Access Makes Agents Smarter45:18 Secure Agent Workflows46:08 The Future of AI Interfaces47:02 Outro