I've watched & re-watched this wonderful 'The Pragmatic Engineer' episode with Kent Beck, and warmly recommend it to anyone whose interests cross over agile and programming and AI, as mine do.

The two industry newsletters I read faithfully are Orosz's and Beck's, so it felt truly serendipitous when this episode landed!

Highlights (for me!)

Kent Beck is a Spurs fan! ⚽️ 🐓

The 'Coding Genie' analogy for Agentic AI (6:15)

You wish for something and you get it, but it's not what you actually wanted, and sometimes it seems like the agent actually has it in for you.

AI Agent dev is "literally an addictive loop"" (9:30)

In that you "click the button" and it works magically, with "intermittent reinforcement, negative outcomes & positive outcomes where the distribution is fairly random, seemingly."

AI dev leverages great product management! (12:30)

You can think really big thoughts, and the leverage of having those big thoughts is just suddenly expanded enormously.

I had this tweet 2 years ago, where I said '90% of my skills just went to $0 and 10% of my skills just went up 1000x'. This is exactly what I'm talking about - having a vision, being able to set milestones towards that vision, keeping track of a design to control the levels of complexity as you go forward, those are hugely leveraged skills now... compared to "I know where to put the & and * and {} in Rust"

TDD as agile programming (Start ~ 42:00, meat at 47:00)

Kent Beck gives a masterful summary of why 'test first' fits his desire to defer commitment, based on the assumptions that he will learn, and thigns will change.

I can understand why you would make that assumption, that you already know what the implementation is going to be.

...and the more correct you are in that assumption, the less value there is to have the test first.

I'm always going to bet, this is the most ignorant I'm ever going to be - today - I'm going to be more experienced tomorrow.

So I assume I'm going to learn, and I'm going to assume things are going to change.

The more those assumptions hold true - the more I have to learn and the more things are going to change - the less commitment I want to make right now, and the more I want to defer commitments to the future.

The more you can predict, the bigger the jumps you can make.

I love it!