Critical analysis of foundational agent architecture for developers building AI systems.
Argues that MCP (Model Context Protocol) is obsolete because modern LLMs can now call APIs directly without needing specialized protocols.
Simon Willison defends MCP's value for controlled agent deployments with security, auth, and audit requirements despite full-access terminal agents making it seem obsolete.
Ethan Mollick predicts AI will enable systematic re-evaluation of all published research and accelerate scientific discovery beyond human absorption capacity.
Critique of LessWrong's intellectual influence on AI, arguing the community that shaped AI thinking has conceptual flaws despite its members' roles in frontier labs and alignment research.
Ethnography of 1990s copier technicians shows work is more complex and improvised than assumed, challenging simplistic AI replacement narratives despite eventual automation.
Simon Willison shares Michael Lynch's advice against AI-generated blandness in software blogging, urging developers to write with personality.
