[LoganDark]

I'm surprised the code has visible LLM smells. Though, I shouldn't be surprised. I hope the important bits are still human-controlled (and the same for Apple's many operating systems that absolutely deserve to remain stable and understood).

[airspeedswift]

I assure you, every inch of the interpreter code has been stared at by humans, a lot. TBH even the assembly generated by it has.

[ahartmetz]

All 150 kloc in six months by two people? Actually, it sounds like way too much code for the task unless 70+% of it is tests.

[dcrazy]

> By the end of the project, we wrote nearly four times as many lines of test code as we wrote for the Swift interpreter itself.

[dgellow]

From what I got Apple is using claude code A LOT internally

[wahnfrieden]

Yes they are using Claude Code - not the Xcode agents.

It worries me. I hope Codex adoption picks up there.

[andrekandre]

thats a shame if true, they really should be dog-fooding that horrible agent ui in xcode to bring it up to a usable state

[dcrazy]

The UI got a massive overhaul in the new Xcode beta. It’s no longer confined to the sidebar.

[wahnfrieden]

Devs continue to be tricked by incremental updates to it. It's still deficient

[wahnfrieden]

A lot of devs are tricked into using it because it’s official

[LoganDark]

I love how it doesn't even support reasoning output or edit tool diffs. (Yes it can show diffs sometimes when using the 100% official flow but not when using ACP)

[wahnfrieden]

It also doesn't support Computer Use or Browser Use among other deficiencies

[Cassell]

It would be interesting to see their internal guidance on LLM use. It’s a massive amount of new power that has to be wielded carefully. That kind of guidance might mean the survival or downfall of some big corps in the next few years.