Episodes tagged: AI

We argue prompt engineering is already on its way out — and what’s replacing it is one of the oldest skills in software. When generating code gets cheap, deciding precisely what to build becomes the whole game.

A quiet split is forming in software teams — not junior versus senior, but developers who’ve learned to work with AI and those who’ve decided not to. We look at what the divide really is, why it compounds, and why plenty of brilliant people are on the wrong side of it.

James explores spec-driven development and how it changes the way developers actually work with AI tools to build better software.

AI can help write code, but it can also make your codebase worse. James explores the pitfalls of AI-generated code and how to avoid them.

As AI becomes embedded in software development, ethical questions arise. James discusses the moral considerations teams should be thinking about.

A gap is forming between teams that embrace AI tools and those that don't. James explores what this divide means for the industry.

AI can generate code quickly, but that code still needs experienced eyes. James explains why senior review remains critical.

LLMs are powerful tools, but they're not junior developers you can just hand tasks to. James discusses how to think about AI assistants correctly.

The AI replacement debate continues. James provides a nuanced take on which jobs are safe and which might be at risk.