hm https://github.com/bluesky-social/social-app/blob/main/CLAUDE.md
-
@erincandescent @res260 @cwebber @airtower
'modulo institutional knowledge' is doing a lot of heavy lifting there since that's half the problem with LLM usage
and the other half of the problem is the assumption that an LLM will produce identical code
so I don't think there's a useful discussion to be had if those are your assumptions
@benjamineskola @res260 @cwebber @airtower Look, I don’t think we’re talking about (original definition) vibe coding here, where nobody is looking at the output. We’re talking about cases where there’s a human in the loop.
If the tool is generating garbage code and the human is accepting it, that’s a human problem more than a tool problem.
I start from this assumption because we assume the human is competent and has taste. I assume they are not just letting the tool run wild on the codebase and make a mess.
There are issues and questions around institutional knowledge (if the human isn’t exploring the codebase in the same way, how much are they learning? how much do you pickup through review vs implementation?) but even then I’d argue that one of the primary criterions with regards to maintainability is how hard it is for a newcomer to pick something up and work on it.
-
@cwebber Ah yes, LLMs are finally good now, this is probably the fourth or fifth time I've heard it and at this point it's like the boy who cried wolf, I'm not even going to bother testing out the LLMs of today to see what they get wrong, I'm just not going to believe their advocates
-
@benjamineskola @res260 @cwebber @airtower Look, I don’t think we’re talking about (original definition) vibe coding here, where nobody is looking at the output. We’re talking about cases where there’s a human in the loop.
If the tool is generating garbage code and the human is accepting it, that’s a human problem more than a tool problem.
I start from this assumption because we assume the human is competent and has taste. I assume they are not just letting the tool run wild on the codebase and make a mess.
There are issues and questions around institutional knowledge (if the human isn’t exploring the codebase in the same way, how much are they learning? how much do you pickup through review vs implementation?) but even then I’d argue that one of the primary criterions with regards to maintainability is how hard it is for a newcomer to pick something up and work on it.
@erincandescent @res260 @cwebber @airtower Except there is a huge problem with people actually just not looking at the code being generated. The wave of slop PRs inundating many open-source projects recently, for example.
People keep saying 'of course there is a human in the loop' but it seems increasingly clear to me that nobody is actually bothering to be the human in the loop themselves.
(Edit: but also, even when people are well-intentioned, I think the LLM-based process just makes it much harder to ensure quality than actually writing the code oneself.)
And yes, this is a human problem, it's all a human problem. But that's like saying 'guns don't kill people, people do'. True, but, the tool clearly exacerbates the problem.
As for your final paragraph I don't remotely see why you think LLMs solve this problem either.
-
@erincandescent @res260 @cwebber I am no fan of tedium for tedium's sake... but why specifically slop machines, which are notoriously unreliable, to solve this problem, aside from all the money that got poured into this technology? Could the same money have been used to develop languages and frameworks with sensible defaults and configurations, thereby eliminating (or vastly reducing) the need for tedium?
@sitcom_nemesis @res260 @cwebber I think there’s a spectrum
There’s code we keep repeating in broadly the exact same structure, just with different details fileld in. That’s boilerplate.
There’s code that’s unique and creative and requires thought. That’s “the meat of the problem”.
But there’s lots of stuff in the middle where it’s not quite creative, doesn’t really require thought, but either because of domain requirements, accidents of history, or just because you’re gluing two libraries together that hadn’t ever seen each other, is too irregular to really code generate but is not actually interesting.
-
@cwebber But honestly bsky web UI felt like a one-shoted ‘vibe-coded’ Twitter clone even before it actually became one.
-
@erincandescent @res260 @cwebber @airtower
'modulo institutional knowledge' is doing a lot of heavy lifting there since that's half the problem with LLM usage
and the other half of the problem is the assumption that an LLM will produce identical code
so I don't think there's a useful discussion to be had if those are your assumptions
@benjamineskola@hachyderm.io @erincandescent@akko.erincandescent.net @res260@infosec.exchange @cwebber@social.coop Yeah, this. If I'm looking at a new tool/library to possibly use (and not do a hard fork on), a key question is: Are there people who understand and care maintaining this thing? Because if there aren't, eventually "hard fork" or "don't use it" will probably be my only choices.
And using LLMs to generate code points towards "no" (or at least "not much") for both understanding and caring. If someone skilled is actually putting in the effort to edit LLM output until it is no worse than what they would've written themselves (point for care at least), chances are it would've been faster (let alone other effects) to just do that. -
@erincandescent @res260 @cwebber @airtower Except there is a huge problem with people actually just not looking at the code being generated. The wave of slop PRs inundating many open-source projects recently, for example.
People keep saying 'of course there is a human in the loop' but it seems increasingly clear to me that nobody is actually bothering to be the human in the loop themselves.
(Edit: but also, even when people are well-intentioned, I think the LLM-based process just makes it much harder to ensure quality than actually writing the code oneself.)
And yes, this is a human problem, it's all a human problem. But that's like saying 'guns don't kill people, people do'. True, but, the tool clearly exacerbates the problem.
As for your final paragraph I don't remotely see why you think LLMs solve this problem either.
@benjamineskola @res260 @cwebber @airtower
Except there is a huge problem with people actually just not looking at the code being generated. The wave of slop PRs inundating many open-source projects recently, for example.
People keep saying ‘of course there is a human in the loop’ but it seems increasingly clear to me that nobody is actually bothering to be the human in the loop themselves.
I know these are problems, but you’re moving the topic of conversation. There have always been bad developers with bad practices shovling crappy code over the fence. LLMs have made this easier and it sucks but it’s not new.
And yes, this is a human problem, it’s all a human problem. But that’s like saying ‘guns don’t kill people, people do’. True, but, the tool clearly exacerbates the problem.
Sure, but lazy/careless people use tool to produce bad results is not a unique problem. It’s very easy with a power drill to make messy holes, but we arent’ forcing everyone to use hand drills.
Saying using these tools results in necessarily bad output is just not backed up by available evidence.
I don’t pretend they’re perfect and I don’t pretend there aren’t problems. What I sense is that they’re not going away and are going to become and remain routine parts of toolboxes long into the future.
-
@benjamineskola @res260 @cwebber @airtower
Except there is a huge problem with people actually just not looking at the code being generated. The wave of slop PRs inundating many open-source projects recently, for example.
People keep saying ‘of course there is a human in the loop’ but it seems increasingly clear to me that nobody is actually bothering to be the human in the loop themselves.
I know these are problems, but you’re moving the topic of conversation. There have always been bad developers with bad practices shovling crappy code over the fence. LLMs have made this easier and it sucks but it’s not new.
And yes, this is a human problem, it’s all a human problem. But that’s like saying ‘guns don’t kill people, people do’. True, but, the tool clearly exacerbates the problem.
Sure, but lazy/careless people use tool to produce bad results is not a unique problem. It’s very easy with a power drill to make messy holes, but we arent’ forcing everyone to use hand drills.
Saying using these tools results in necessarily bad output is just not backed up by available evidence.
I don’t pretend they’re perfect and I don’t pretend there aren’t problems. What I sense is that they’re not going away and are going to become and remain routine parts of toolboxes long into the future.
@erincandescent @res260 @cwebber @airtower > LLMs have made this easier and it sucks but it’s not new.
So why would we want to make it worse?
> Saying using these tools results in necessarily bad output is just not backed up by available evidence.
Every output I've seen from these things has been, at best, no better than a human would have done. And that's being generous.
> What I sense is that they’re not going away and are going to become and remain routine parts of toolboxes long into the future.
This is a self-fulfilling prophecy. Of course they won't go away if people insist on defending them.
-
@benjamineskola@hachyderm.io @erincandescent@akko.erincandescent.net @res260@infosec.exchange @cwebber@social.coop Yeah, this. If I'm looking at a new tool/library to possibly use (and not do a hard fork on), a key question is: Are there people who understand and care maintaining this thing? Because if there aren't, eventually "hard fork" or "don't use it" will probably be my only choices.
And using LLMs to generate code points towards "no" (or at least "not much") for both understanding and caring. If someone skilled is actually putting in the effort to edit LLM output until it is no worse than what they would've written themselves (point for care at least), chances are it would've been faster (let alone other effects) to just do that.@airtower @res260 @benjamineskola @cwebber I still see LLM related artifacts as a negative quality signal. There's lots of crap LLM aided code out there and there's lots of people slopping stuff together. The worst developers are disproportionality interested.
But I think there's a lot of stuff being written with LLM assistance these days where you'd not be able to tell -
@airtower @res260 @benjamineskola @cwebber I still see LLM related artifacts as a negative quality signal. There's lots of crap LLM aided code out there and there's lots of people slopping stuff together. The worst developers are disproportionality interested.
But I think there's a lot of stuff being written with LLM assistance these days where you'd not be able to tell@erincandescent@akko.erincandescent.net @res260@infosec.exchange @benjamineskola@hachyderm.io @cwebber@social.coop That might be, but as I wrote in that case I doubt there's any benefit (like faster progress) to the developer (even looking at code only, ignoring all the harmful side effects of LLMs).
-
@airtower @res260 @benjamineskola @cwebber I still see LLM related artifacts as a negative quality signal. There's lots of crap LLM aided code out there and there's lots of people slopping stuff together. The worst developers are disproportionality interested.
But I think there's a lot of stuff being written with LLM assistance these days where you'd not be able to tell@erincandescent @res260 @cwebber @airtower Given that every output of LLMs that I've seen that is identifiable as such has been mediocre at best, why would I assume without any evidence that there's a significant quantity of LLM-generated code that's actually good?
"There's no evidence of it but it's definitely there" is unpersuasive.
And I've also found that people's evaluations of LLM-generated code quality is wildly out of step with my own evaluations, so I would not automatically assume that because someone says it's good that it's actually good.
And then, even if the code was of acceptable quality, the negative effects on the process (increased difficult of reviewing
decreased institutional knowledge, among other things) count against it too.(And all of this is setting aside the ethical issues, which in practice I don't think we should do anyway. Like, even if LLMs produced good output they'd be ethically indefensible, and even if they were ethically acceptable the results are so poor that why would you bother with them?)
-
@cwebber I found LLM generated code in vim today
-
-
I have this suspicion that the ATproto stack, at least the stuff from Bluesky, is heading towards "majority-vibecoded" but that's mostly just from seeing a lot of posts from the Bluesky eng team rather than me having spent much time in the codebase
Why is def hugely responsible for Bluesky/ATProto's design and if *he's* mostly letting Claude write 99% of his code, the rest of the eng team is likely to be heading in that direction too?
Also https://bsky.app/profile/pfrazee.com/post/3meogr22l3k2d
> A year ago, I thought LLMs were kind of neat but not that useful. I saw the code autocomplete and thought, meh.
>
>Last summer just flipped. I never ever thought I would see automated code generation like we see now.
>
> I know there’s baggage but you need to know the coders are being real about this -
Also https://bsky.app/profile/pfrazee.com/post/3meogr22l3k2d
> A year ago, I thought LLMs were kind of neat but not that useful. I saw the code autocomplete and thought, meh.
>
>Last summer just flipped. I never ever thought I would see automated code generation like we see now.
>
> I know there’s baggage but you need to know the coders are being real about this -
@cwebber yeah, least surprising Bluesky thing to do
-
@erincandescent
@res260 @cwebber we have tools for that tho? templates and libraries and bootstrapping and automation tools. they don't have to be, as @olivia so said a couple month ago "made from shit and blood" -
@erincandescent
@res260 @cwebber we have tools for that tho? templates and libraries and bootstrapping and automation tools. they don't have to be, as @olivia so said a couple month ago "made from shit and blood" -
-
Example: https://bsky.app/profile/why.bsky.team/post/3meomclcfss2w
> Until December of last year I was using LLMs as fancy autocomplete for coding. It was nice for scaffolding out boilerplate, or giving me a gut check on some things, or banging out some boring routine stuff.
>
> In the past two months Claude has written about 99% of my code. Things are changing. Fast@cwebber oof, always wonder what review processes are in place at places where a large portion of changes have been vibecoded. I tend to discuss why a certain implementation has been picked, what pitfalls have been considered, if a solution is adequate to a problem etc. when reviewing major changes with engineers whose code I review, "claude did that" wouldn't really stand as an answer in my book. Makes me wonder if that kind of discussion just isn't common anymore? this whole agent stuff just seems like a big footgun to me that will inevitably lead to hard to comprehend and more difficult to navigate/to maintain codebases
