Developers May Stop Depending on Libraries

Developers May Stop Depending on Libraries

From Agentic Conversations (formally mlops.community) by Demetrios

July 6, 2026 · 47 min

About this episode

The episode discusses the impact of AI on software development and the evolving role of developers in an era of advanced language models.

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/smithshaun Demetrios: https://www.linkedin.com/in/dpbrinkm Hugging Face: https://huggingface.co ⏱️ Timestamps[00:00] Introduction [01:56]…

People in this episode

Host: Demetrios

Guest: Shaun Smith

Topics covered

  • AI coding
  • reinforcement learning
  • open source AI
  • software development
  • language models
  • autonomous agents

Keywords

  • reinforcement learning
  • MCP
  • Fast Agent
  • AI-powered tools
  • software architecture
  • open-weight models
  • programming future

Mentioned in this episode

Organizations: Hugging Face

More episodes of Agentic Conversations (formally mlops.community)

Explore listener stats, chart rankings, contacts and more on the Agentic Conversations (formally mlops.community) podcast page.