I keep reading the headline as “copulating” and giggling. Sorry.

For your team of developers to deploy at the speed and scale that you need to lead in the market, your developers must be empowered with AI at every step of the software development life cycle, customized and fine-tuned to your codebase.

I feel like I know who the target audience for this post is, and it’s not programmers

the strange thing about copilot is that it is about writing code but github isn’t a code-writing product (besides that text editor they made), it’s a version-control & repository product.

through my deeply-rabbit-holed-product-design-theoretical-perspective lens this translates as another manifestation of trying to make something that is concrete in purpose, which gives concrete accountability to the company behind it, into something general in purpose, which dilutes the concrete acocuntability over time.

“This is a public/private version-controlled repository product”

vs

“This is a collaboration and productivity product”

relatedly, I recently had to work on a project in a language I’ve barely touched before. also happened to notice that apparently I have free copilot “because of my open source contributions” (??? whatever)

so I tried it out

it was one of the usecases people keep telling me it’s ideal for. unfamiliar territory! a new language! something I have little direct experience in but could possibly navigate by using some of my other knowledge and using this to accelerate!

well, it managed to perform just about exactly to my expectations! I didn’t really try hard to take down numbers but I’d say easily 30%+ simple (and possibly subtle?) errors, and suggestions being completely wrong 60%+. the mechanic for the latter is the same bullshit as they push with prompts, “choose the one you like best” > “cycle through the completion suggestions”

observed things like logic inversions and incorrect property references, both of which are things I don’t know whether a learning-to-program person someone using it in the “this is magical! I can just make it type code for me!” sense would be able to catch without some amount of environment tooling or zen debugging (and the latter only if/when they get into the code reading mindset). at multiple points, even when I provided it with extremely detailed prompts about generation, it would just fail to synthesise working biz logic for it

and that was all for just simple syntax and language stuff. I didn’t even try to do things with libraries or such. I’m gonna bet that my previous guesses are also all fairly on point

all in all: underwhelming. I remain promptdubious.

I’d still like to start an awful.systems sub for folks to discuss their own open source projects (and in the, what, month or so since I proposed it I’m still stuck on finding a good name), but alongside that it’s becoming very clear that our projects will need a home that isn’t github. I’m having a hell of a time finding an alternative that:

• doesn’t suck for reading code and docs (everything, even GitHub itself lately, fails here, even though it’s what I spend 90% of my non-work time in github doing)
• supports pull requests

there are some nice to haves that so far nothing seems to have:

• if we need to host it as part of awful.systems, setting it up and administrating it shouldn’t fucking suck. it feels like a decentralized app that comes with the repo and supports local hosting would be a good complement for git, but everything I’ve seen that tries this is fucking awful to use (hello fossil)
• federation would be amazing. there’s actually a protocol some folks are developing to federate across code forges (aka github clones), but it seems like it’s far from done
• maybe it also shouldn’t be ugly as fuck? like I’m not expecting much but it’s not charming how many of these look like some shit from the 90s nobody’s nostalgic for