[DanielVZ]

On the other hand I’m pretry sure you will need senior engineers not only for designing but debugging. You don’t want to hit a wall when your Agentic coder hits a bug that it just won’t fix.

[nopinsight]

There’s a recent article with experiments suggesting LLMs are better at bug fixing than coding, iirc. It’s from a company with a relevant product though.

[eru]

Why do you expect AIs to learn programming, but not debugging?

[ZephyrBlu]

1) Debugging is much harder than writing code that works

2) AIs are demonstrably much, much worse at debugging code than writing fresh code

Ex: "Oh, I see the problem! Let me fix that" -> proceeds to create a new bug while not fixing the old one

[eru]

Debugging is harder for humans, too.