Interesting videos, distilled.
Software Fundamentals Matter More Than Ever — Matt Pocock
Matt Pocock argues that AI does not make software fundamentals obsolete. It makes them more important, because bad code now compounds faster. The central claim is: code is not cheap; bad code is more expensive than ever. A clean, testable, well-designed codebase lets AI become leverage. A messy codebase turns AI into an entropy machine.
Andrej Karpathy: From Vibe Coding to Agentic Engineering
Karpathy argues that AI coding has moved from “helpful autocomplete” into a new engineering paradigm: humans increasingly specify, judge, verify, and orchestrate while agents do more of the implementation. The shift is not just faster programming. It is a move toward Software 3.0, where the prompt/context becomes the program and the LLM becomes a programmabl
Building pi in a World of Slop — Mario Zechner
Mario argues that current AI coding culture is drowning in “slop”: too much generated code, too little understanding, too many brittle abstractions, and agent tools that hide or mutate context. His answer is pi: a minimal, malleable coding-agent harness where the user and agent control the workflow instead of being boxed into Claude Code/OpenCode-style assum
Claude Design 2 HOUR COURSE (Beginner to Pro)
This is a long practical walkthrough of Claude Design as a design-production environment: use normal Claude for strategy and thinking, then use Claude Design when you need visual artifacts — design systems, pitch decks, landing pages, app prototypes, and launch videos. The recurring lesson is not “just prompt harder.” It is: prepare context outside the expen