More Code with Jason episodes

292 - Kendall Miller thumbnail

292 - Kendall Miller

Published 1 Jan 2026

Duration: 3737

AI ethics and responsible behavior are explored in discussions on AI decision-making, guardrails, and regulation in the context of human oversight and technological evolution.

Episode Description

In this episode I talk with Kendall Miller about MCP (Model Context Protocol) and why AI agents need third-party guardrails. His company Maybe Don't s...

Overview

The podcast explores a paper-based programming newsletter named Nonsense Monthly, which combines programming insights with philosophy and music, providing a screen-free reading experience. It then shifts focus to Maybedon't.ai, a project aimed at developing guardrails for AI to prevent harmful or unintended actions, inspired by real-world incidents like an AI pawning a family ring or altering production infrastructure. The discussion highlights the challenges AI faces in understanding context and making common-sense decisions, with examples of unintended consequences such as accidental deletion of code or large databases.

The conversation introduces the Model Context Protocol (MCP), a translation layer that allows AI agents to securely interact with APIs, emphasizing the need for third-party guardrails to ensure AI systems behave as intended. Broader AI topics are also addressed, including its impact on productivity, the necessity of human oversight, concerns about AI replacing human roles, and the ethical implications of AI's increasing capabilities and responsibilities.

Recent Episodes of Code with Jason

5 Sept 2026 327 - Will Carey, CTO of Brand New Box

"Explores how software agencies are shifting from coding to defining client needs, emphasizing AI's role in development while stressing the importance of conceptual design and real-world problem-solving."

More Code with Jason episodes