When you dogfood your own Rube Goldberg machine.

I'd have thought someone who's so enamoured with the tech would have at least a basic understanding of how it works.

So you've evaluated all the sources that the model was trained on initially have you? How long did that take you?

> I'm shipping quality software and features to my customers at a pace I haven't been able to before.

I'm sorry are you agreeing with me or not? It sounds like you're agreeing with me.

Exactly.

LLM bros are just the new blockchain/crypto bros, but they aren't necessarily even writing their own spruiking comments any more.

I played with Image Playground last year some time. It was really fun. You know why? I can't draw, and I can't paint, to save my life. It's letting me do something I can't do well/at all on my own.

Using an LLM to do something I can do, with the caveat that it's pretty mediocre at the task, and needs to be constantly monitored to check it isn't doing stupid things? If I wanted that I'd just get an intern and watch them copy crappy examples from StackOverflow all day.

The same logic explains the use of LLM's to write emails/other long form text.

It makes accessible something that people otherwise cannot do well. Go look at submissions on community writing sites. The people who write because they're good at it, are adamant they don't use an LLM.

People use LLM's to do things they're otherwise not able to do. I will die on this hill.

What's your definition of "successfully"?

More LOC committed per day is probably the only one that's guaranteed when you let spicy autocomplete take the wheel.

I don't think it's at all possible to reason about the other more meaningful metrics in software development, because we simply don't have the context of what each human is working on, and as with the WYSIWYG fad of 3 decades ago, "success" is generally self-reported, by people who don't know what they don't know, and thus they don't know what spicy autocomplete is getting woefully wrong.

"But it {compiles,runs,etc}" isn't a meaningful metric when a large portion of the code in question is dynamic/loosely typed in a non-compiled language (JavaScript, Python, Ruby, PHP, etc).

The Spicy Autocomplete koolaid club is out in force today I see.

We clearly have different ideas of what the word "intelligent" means.

Is there anything about this that is actually git specific or could it work with eg Mercurial?

Why buy a second extra machine to do testing of multi machine infrastructure configurations when my workstation can run the VMs locally?

For others? I don't know that's why I think it's ridiculous to assume everyone else's use case is the same as your own.

Imagine thinking everyone who buys a Mac and runs VMs wants to run heaps of macOS VMs.

I've never hit the referenced limit because it isn't a limit on running VMs it's a limit on running macOS, and I hardly ever run macOS VMs.

I'm not sure why people don't use Mac's are so obsessed with telling people who do use Macs that they're wrong, and yet here we are.

Currently "I don't know how to configure xdebug so I wrote a convoluted alternative" is tied for top place with "I don't know how MySQL sockets work so I rewrote the entire thing to use Mongodb".

You store a TOTP secret on your ....

It's less PII than an ssh public key because it's literally just a random string, that *they* generated, and you only need it for the web UI.

So please tell me how the Americans are going to track and identify you through a fucking TOTP secret.