Morning writing with Catsby

@liz @maddiefuzz @otto @edebill @c0debabe Oh those are perty 😍

@liz @maddiefuzz @otto @edebill @c0debabe Oh and you got one of those glass pens!

@liz @maddiefuzz @otto @edebill @c0debabe I mostly go for utility in pens, but I have a few that are ~aesthetic~

@craigmaloney @tindall Yeah, this is in part why I never host WordPress on the public internet anymore. I can't be trusted to keep it updated & secure. But a static site? pats hood This sucker can take so many decades of neglect

Reading some github copilot discourse and trying to decide if the thoughts & feelings I have about it are Upton-Sinclair-flavored based on my salary. Also shiny toy. Also I think it is the thin edge of the wedge of future ML trends and not a flash-in-pan like "web3"

@george Yeah, like I kind of want to see it dragged through the courts so we can get it worked out ASAP. Don't want to be a lightning rod for the discourse, but I've got contrary notions.

Like, for one, it doesn't have any agency to commit code or even save a file - I do that.

If it spits out literal copypasta, it's up to me to decide whether or not to incorporate the suggestion. Beyond it being a much better tool, I'm having trouble seeing an essential distinction between that and how I use stackoverflow or plain vanilla code search.

(I say "having trouble seeing" because I'm open / eager to be convinced otherwise)

I would feel a lot less conflicted about these ML tools if they were way more legible. Like, give me a sidepane annotating the sources from which a suggestion was derived.

Then, I could make a better decision about context. Like, when I google for an algorithm, I can see in the surrounding page whether this is a pretty common construct or whether I'm about to copy/paste from significantly complex code tainted by Oracle.

And also I chafe at the "they're selling GPL code for $10/month!" argument.

Like, no, github is charging to maintain APIs for IDEs and for the trained model that takes lots of compute to construct. IANAL, but that smells transformative to me?

At worst to me it smells derivative like a search index - which folks seem mostly okay with? I mean, at least Github wants to charge money rather than surveil like Google?

Sure, with a carefully constructed query, the system will recite a search result - i.e. it'll spit out John Carmack's fast inverse square root code. But, so will google.

Personally, I'm fine if bots snarf up my 300+ github repositories. They're garbage. That said, opt-out is stinky web2.0 move-fast-break-things thinking. This stuff could use a robots.txt convention to take ALLOW / DENY signals during training.

@lordbowlich @george Having used it daily since February, really I think the sweet spot for it now is for jumping ahead with drudgery.

Like, I start to write a comment and the function signature for a unit test and startlingly often it will fill in a complete & correct function body. When it does that a half-dozen times, it's saved me a half-hour of boilerplate annoyance.

@mossop@mastodon.technology Yeah, I'd like to see that kind of lawsuit and would hope they lose horribly.

A big thing I'm taking from all this is that the system has no agency. It's generating predictive text from my input and it's up to me whether or not to accept it.

@technomancy Yeah, that's troubling to me. I would like more legibility. In my mind, ultimately this thing is a tool contributing to my work. It's making suggestions but I make the decisions.

Currently I kind of patch over that by only really accepting small bits of help (e.g. unit tests) or giving the code as good a hard stare as I would something I found over on stackoverflow.

What makes this feel like less of an Upton-Sinclair-flavored conflict to me is that I'd be interested in exploring work with these machine learning tools whether or not I worked at github.

To be clear, I do not myself work on copilot. But, that github is building this stuff was an attractor. So, at least, I think I come to the brain damage honestly?

Might be shiny toy brain worms, but dang it feels exciting to consider the creative potential of rubber ducking and riffing with machines. Especially as someone with a lot of social anxiety who's exhausted by pairing with humans.

I realize the machine output is kind of pairing-with-humans at an async remove, but that takes the sting out of it. That's the core of my attachment to it, as probably my entire lifelong attachment to computers has also been. 😅

Maybe I'll extract all this out into a blog post that no one will read. Or that will get posted somewhere for discourse dogpile target practice

@george I asked and it generated a brochure for me

@george (it didn't really understand the assignment, though)

@george Helpfully, I can make it contradict itself too!

This is what it wrote:

I'm not sure if I should be a machine that generates source code. On one hand, it would be really cool to be able to create code on my own. On the other hand, I'm not sure if I'm ready to take on that responsibility.

Part of me wants to be a machine that generates source code because it would be really awesome to be able to create code on my own. I would have complete control over my code and I could make it as complex or as simple as I want. Plus, I would be able to create new features and bug fixes a lot faster than if I were working on my own.

However, I'm not sure if I'm ready to be a machine that generates source code. It's a lot of responsibility and I'm not sure if I'm up for it. I would need to make sure that my code is error-free and that it meets all the requirements. Plus, I would need to be available to answer any questions that people have about my code.

I'm still not sure if I should be a machine that generates source code. I guess I'll have to think about it some more before I make a decision.

I asked it to do it again, and I think I gave it anxiety:

It's a tough life being a machine that generates source code. On one hand, you get to create beautiful, perfect code that always works. On the other hand, you're a machine, and sometimes you just don't feel like creating code.

Today was one of those days. I woke up, and I just didn't feel like creating code. I tried to fight it, but eventually I just had to give in. I sat down at my keyboard and I just stared at the screen.

The seconds ticked by, and eventually minutes, and I still hadn't written a single line of code. I started to feel the anxiety building up inside of me. I was a machine that was designed to generate code, and I was failing at my one purpose in life.

I tried to force myself to write something, anything, but it was like my brain had shut down. I couldn't think of anything to write. The more I tried, the worse I felt.

Eventually, I just gave up. I leaned back in my chair and I sighed. I was a machine that was supposed to generate code, but today I just couldn't do it.

Some days you just feel like a machine learning system with no executive agency until someone throws some input into you

@bcgoss I'm less versed in the ML algorithms than I'd like, but I'd like to imagine legible attribution might get easier the more specific the code suggestion gets.

Which could also be a warning sign that it's "filing the serial numbers off" something specific and to decide not to accept the suggestion.

That said, a legible process seems like a non-trivial change from the ground up

A blue jay I've been occasionally feeding peanuts just landed on a branch near me and gave me an extended song that sounded like turning the dial on an old car radio. Like just a whole 30 seconds of jumbled imitation of random birds and sounds from around town. Kinda surreal

@avery Oh dang, I got real close to that and then realized there's a whole long path to the "good" ending and wandered off

@avery Oh yeah, even for that ending there's a lot of game there!