https://acoup.blog/2025/08/22/collections-life-work-death-an...

Last year was the first time I saw an AI agent actually debug and fix a non-trivial bug in a satisfactory way. Even then, trying to use it on larger tasks made it clear that it wasn't something I could just hand over the issue tracker to.

Now? I've been using Codex for the past several months to work on a nontrivial project. Which was prototyped in C++ (for library reasons mostly), then had the initial version written in Haskell, and more recently I got it ported to Rust to keep memory use in check on mobile.

These things are not trouble-free, but the sheer amount of progress made in just the last year alone is astounding. Skepticism is well and good, but healthy skepticism ought to yield to tangible evidence.

That has been the case for the last, oh, decade or so. Where do you think LLMs learned to slop code?

In the absence of such an entitlement, not volunteering to disclose the tools used is not fraud.

Also, humans do use em dashes, just FYI.

And I'm not arguing that Claude has personhood. The point is that Anthropic is regularly making arguments that seem to imply that.

But you can have a Linux kernel running in a VM on macOS as well, and while it doesn't have something like WSL built-in, it provides enough foundation for others to build it: https://lima-vm.io/docs/

I run Linux in Lima VMs regularly on macOS for development, and I find that it works very well in practice despite not being first-party.

Assuming they are kept updated. Unfortunately, the way macOS works is that Apple expects developers to constantly update their apps to keep them working on newer macOS versions, and for games especially this is often not the case a few years after the release.

Worse yet, many titles are marked as working, but if you actually try to use them, various things break, e.g. hi-DPI.