this post was submitted on 09 Nov 2023
9 points (100.0% liked)

TechTakes

1491 readers
126 users here now

Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

founded 2 years ago
MODERATORS
 

will this sure is gonna go well :sarcmark:

it almost feels like when Google+ got shoved into every google product because someone had a bee in their bonnet

flipside, I guess, is that we'll soon (at scale!) get to start seeing just how far those ideas can and can't scale

top 17 comments
sorted by: hot top controversial new old
[–] [email protected] 6 points 1 year ago

I keep reading the headline as "copulating" and giggling. Sorry.

[–] [email protected] 5 points 1 year ago

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

[–] [email protected] 4 points 1 year ago

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"

[–] [email protected] 2 points 1 year ago (1 children)

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.

[–] [email protected] 2 points 1 year ago

Yeah, that always perplexed me. Copilot is a terrible tool if you're using it in a domain you aren't already proficient in, because it will mess up. And even worse, it'll mess up in subtle ways that most people wouldn't do themselves. You need to know what you're doing to babysit it and ensure it doesn't fuck everything up.

[–] [email protected] 2 points 1 year ago

Since I'm using D for most of my coding projects, Copilot is mostly useless. I can do boilerplate stuff with metaprograming way easier and at a way more consistent pace, not to mention it's easier to modify. And at least ChatGPT, does not know what to do with D attributes, and just randomly puts them everywhere for functions, since it's way less of an AI than how tech people try to sell it (statistical probability based on Markov chains and some small context windows rather than actually understanding what it does).

[–] [email protected] 0 points 1 year ago (3 children)

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
[–] [email protected] 3 points 1 year ago* (last edited 1 year ago) (1 children)

Have you heard of https://forgefed.org/ yet? It's an activitypub extension for developing git forges. Forgejo (from the codeberg people) is currently implementing federation with it.

[–] [email protected] 3 points 1 year ago

I think I saw a mastodon post about an early version of it, but it’s exciting that it seems to be progressing quickly! that might make Forgejo (and codeberg for a hosted version) a contender — I’ll dig a bit deeper and see how it works. in the worst case, forgefed might be the enabling technology for the kind of software I’d like to use

[–] [email protected] 1 points 1 year ago (1 children)

Is there anything wrong with Gitea?

[–] [email protected] 1 points 1 year ago

it felt fucking awful to administrate last time I tried, but it’s been a good few years

[–] [email protected] 1 points 1 year ago (1 children)

I've been on-and-off trying to get gittorrent packaged for Nix. I don't really care about Web-oriented forge workflows; I fully acknowledge that I'm something of a curmudgeon in that respect.

[–] [email protected] 1 points 1 year ago (1 children)

that actually seems fantastic and at least somewhat amenable to the establishment of a web UI (akin to how torrent trackers extract metadata about torrents, but more focused on the content of the repo). is it a nightmare to make a nix package for?

[–] [email protected] 1 points 1 year ago (1 children)

It's not a nightmare, but I've yet to succeed. npm2nix and node2nix struggle. napalm puts up a good effort, but doesn't quite work either. The biggest sticking point right now is that cjb used a custom DHT implementation with some patches, and I've gotta integrate that somehow.

I will be overjoyed if somebody else writes a working Nix flake. I've tried three times so far, and I bet it'll take five total.

[–] [email protected] 3 points 1 year ago* (last edited 1 year ago) (1 children)

I might give gittorrent a closer look as soon as some of my time frees up. packaging complex node stuff for Nix is always a bit of a pain, but it’s a pain I’m now very familiar with

e:

A method for registering friendly usernames on Bitcoin's blockchain, so that a written username can be used to find a user instead of an ugly hex string.

ugh I hate this part, but hopefully there’s a way to do something like what Mastodon and Lemmy do for external identity verification

[–] [email protected] 3 points 1 year ago (1 children)

isn't that literally the Ethereum Name Service but bitcoin

[–] [email protected] 3 points 1 year ago

unfortunately yes