I just watched Apple's introductory agentic coding video for Xcode 26.3, and my takeaway is it adds a huge cognitive load to programming.

From my perspective, instead of figuring out how to do something and using that knowledge going forward on future projects, a programmer is reduced to acting as a babysitter to figure out if the agent did things correctly, and then spending a lot of effort reviewing the generated code to see if it is even correct.

More work, less knowledge—agentic coding is not the solution.

https://developer.apple.com/videos/play/tech-talks/111428/

#Apple #Xcode #agentic

Meet agentic coding in Xcode - Tech Talks - Videos - Apple Developer

Discover how Xcode 26.3 seamlessly integrates coding agents like OpenAI Codex and Claude Agent to work together on complex, multi-step...

Apple Developer

@puppethead It’s bad enough with the current autocomplete where I’m often correcting what it presented. Sometimes easily, other times I have to outright reject what it’s handing me.

I can only imagine what something worse will be like. I haven’t updated yet.