An interview with ChatGPT. Do you see this changing in the near future as agentic LLM models will be working on behalf of users? Yes — very likely. This would shift the landscape from passive RSS tools to active personal browsing assistants that legally act in your user context. It’s a promising direction, especially with privacy-respecting local models or trusted cloud agents.
One aspect of this vision of the agentic web was Microsoft’s commitment to the Model Context Protocol created by Anthropic; Scott told Nilay Patel in an excellent interview in The Verge that while MCP wasn’t exactly what he would have designed from scratch, ubiquity is more important than semantic differences, particularly when you’re trying to create HTTP for AI agents.