hm https://github.com/bluesky-social/social-app/blob/main/CLAUDE.md
-
@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
-
@erincandescent @res260 @cwebber respectfully, that's not my experience
If the task is specific enough to require human intervention, then it shouldn't be left to a stochastic code generator either -
@erincandescent @res260 @cwebber with the hundreds of billions of dollars burned to make stochastic code generators that only sort of work (and at horrific ethical costs), i dare say that we could have developed adequate tooling instead, and we still can
-
@erincandescent @res260 @cwebber with the hundreds of billions of dollars burned to make stochastic code generators that only sort of work (and at horrific ethical costs), i dare say that we could have developed adequate tooling instead, and we still can
-
@erincandescent @res260 @cwebber i mean a lot of people are agreeing to use the one llm right now, it seems
-
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 Is there something funky going on? bsky seems to be down, at least in Europe.
And the post seems blocked by a labeler in blacksky https://blacksky.community/profile/did:plc:ragtjsm2j2vknwkz3zp4oxrd/post/3meogr22l3k2d
-
Welp, there we go https://bsky.app/profile/why.bsky.team/post/3mgaqaaisfs2e
> Oh interesting, people who don’t know how to build software are getting mad at my post about building software. Cute.
>
> Let me be clear, over the next year, the job of software engineer will shift dramatically to no longer have typing syntax into an editor as its primary time sink. -
Welp, there we go https://bsky.app/profile/why.bsky.team/post/3mgaqaaisfs2e
> Oh interesting, people who don’t know how to build software are getting mad at my post about building software. Cute.
>
> Let me be clear, over the next year, the job of software engineer will shift dramatically to no longer have typing syntax into an editor as its primary time sink.@cwebber yeah he's still his insufferable arrogant idiot self
-
Welp, there we go https://bsky.app/profile/why.bsky.team/post/3mgaqaaisfs2e
> Oh interesting, people who don’t know how to build software are getting mad at my post about building software. Cute.
>
> Let me be clear, over the next year, the job of software engineer will shift dramatically to no longer have typing syntax into an editor as its primary time sink.@cwebber Typing is their primary timesink while developing? Not thinking?
