I’m back after a month away from the podcast, as life got pretty hectic lately. But I’m excited to share what I’ve been thinking about, especially regarding a topic that sparked some interesting conversations on social media.

In this episode, I dive deep into a claim that’s been on my mind: vibe coding is fundamentally probabilistic, while traditional programming is deterministic. And no, before you think I’m against AI-assisted development—I’m not. What I want to do is help you understand the crucial difference between these approaches so you can make informed decisions about how to use them responsibly.

We’ll walk through what probabilistic and deterministic systems actually mean, examine how they apply to both vibe coding and manual code writing, and explore what that trade-off really costs you. I also share some personal updates about streamlining my machine learning workflow for graduate school.

Whether you agree with my take or not, I’d love to hear your thoughts. Comment them down below!

Episode Timestamps:

- 0:00 — Introduction and update on my MSc in Responsible AI journey

- 6:55 — Main topic introduction: Vibe coding vs. traditional programming

- 8:08 — Defining probabilistic vs. deterministic systems

- 10:59 — How this applies to vibe coding

- 12:31 — How this applies to traditional programming

- 16:40 — Why people think traditional programming is probabilistic

- 20:24 — The accountability question and trade-offs

- 21:14 — Wrapping up the core argument

Thanks so much for tuning in—it means a lot to have you here. If this resonates with you, I’d really appreciate a like or share to help this conversation reach more people who care about responsible AI development.

Looking forward to hearing your perspective in the comments, and I’ll catch you on the next episode.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit ai.kuya.dev