Honestly it's such a weird feature, if you're doing complicated redirects like this in nginx where PCRE is necessary, you should do it in your application code. And if you need speed use ngx_http_lua_module.

Am I missing something here? Maybe I'm missing a subtle detail.

And also this chart is super weird:

    Solution  Latency  HiDPI    Native Integration  Setup Complexity
    Cocoa-Way Low      Yes      Native windows      Easy
    XQuartz   High     Partial  X11 quirks          Medium
    VNC       High     No       Full screen         Medium
    VM GUI    High     Partial  Separate window     Complex

I also looked at some of the code and it's using OpenGL 3.3 Core which is... super old. But it makes sense in the context of this being LLM-generated since most of its training data is probably OpenGL 3.3 Core code....

Overall this project is very strange. It makes me feel more confident in my skills, AI isn't all that great. It's all hype. You can get to the frontpage of HN. And if you're Peter Steinberger you can get acquired by OpenAI for a billion dollars. But that's about it. The code isn't getting any better.

This reminds me of that C-compiler-in-Rust publicity stunt by Anthropic. There's no substance. It's just a headline.

I started with Windows 98. Didn't experience OSX until 2010. 9 years wasted.

It didn't need to be a bash script. It could have been written in any scripting language. I presume it started off as a bash script because that's probably what it started out as when he was exploring the idea. And since it was already bash I guess he decided to just keep going with it. But it was just one of those things where I was like, these autocomplete services would never stop and tell you "maybe this 500-line script should be rewritten in python", it will just continue to affirm you, and pile onto the tech debt.

I used to freak out and think my days were numbered when people claimed they stopped writing code. But now I realize that they don't like writing code, don't care about getting better at it, don't know what good code looks like, and would hire an engineer if they could. With that framing, whenever I see someone say "Opus 4.6 is nuts. Everything I throw at it works. Frontend, backend, algorithms—it does not matter." I know for a fact that "everything" in that persons mind is very limited in scope.

Also, I just realized that there was an em-dash in that comment. So there's that. Wasn't even written by a person.

I think it's the big investors' extremely powerful incentives manifesting in the form of internet comments. The pace of improvement peaked at GPT-4. There is value in autocomplete-as-a-service, and the "harnesses" like Codex take it a lot farther. But the people who are blown away by these new releases either don't spend a lot of time writing code, or are being paid to be blown away. This is not a hockey stick curve. It's a log curve.

Bigger context windows are a welcome addition. And stuff like JSON inputs is nice too. But these things aren't gonna like, take your SWE job, if you're any good. It's just like, a nice substitute for the Google -> Stack Overflow -> Copy/Paste workflow.