This is barely slop. It’s about triaging issues and updating dependencies. Not actually creating slop commits. I think this is a bit of a nothingburger.
At this point I just give up. You make your whole workflow around something and then a week later an AGENTS.md is commited to the repository
I’d still try to avoid it when there’s alternatives but damn this is so tiring
I think it’s fine to use AGENTS files to waste tokens of slop contributors
Its existence doesn’t necessarily suggest the projects uses AI
Yeah there’s is some of those, but a lot of people just don’t click to read it
I understand LLMs provide a boost for devs to write code when used as a completion, but I feel it’s a very slippery slope once you start using it, eventually devolving into more work being passed straight through the LLM without much human supervision, so bugs can frequently slip by.
Recently I’ve been annoyed by lower software estability and I’ve seen it starts to drop as soon as an LLM is used heavily for development. Recent example: The newsblur android app, it would crash if I tapped on a subscription group, a paid feature I don’t have but often misclick. Out of curiosity checked their github and lo and behold, main dev has been using Claude for many months.
The reality is that LLMs are massive force multipliers for a competent dev team. They’re largely garbage in other areas, but programming is one where they have clear, obvious benefits when used in a thoughtful way.
It is important to note that there are a lot of load bearing adjectives in those sentences and any usage of LLMs also needs to be weighed against it’s clear, obvious societal harms. It’s going to take a little bit of time for legislature and society to catch up to technology, but I have some hope still.
* in a thoughtful way (which most devs are terrible at)
* in the short/medium term (because they atrophy reasoning skills and cut off upskilling opportunities for more junior staff)
* while still having to maintain your skills to catch out the many inevitable issues
* while trying to maintain the morale doing the least enjoyable thing about programming every day - reading someone else’s code
* while managers press you to review more code, more quickly beyond what is possible to actually review
* with dubiously evaluated productivity gains, ignoring tech debt and dangerous lack of whole codebase knowledge
* with uncertain future financial burden as key business pipelines are hurriedly sloppified with no real purpose or plan
* living with the moral burden of funneling money directly into the pockets of deranged American technofeudalists and a Taiwanese fuckboy in a bad leather jacket
Does that cover all the caveats?
More or less, though I would argue that some of these aren’t actually a problem with the LLMs themselves. Specifically, the issues with management and “enslopification”. I would also push you to think more on which parts of this are purely your own dislikes - I, for example, actually enjoy reviewing other people’s code.
That said, I don’t disagree that LLMs are largely being used in ways that are not useful or helpful. However, I believe that time will show those uses as the harm they are. Businesses that went too hard on it will have to spend huge amounts of money to backtrack and some will not survive the endeavor. Aside from the scale, this isn’t too different from the crypto and blockchain nonsense that popped up everywhere when those were the hot new tech. A lot of companies will fail and a lot of time and money will be wasted in the process.
I’m trying to have a nuanced opinion about this. I do think that LLMs are pretty bad, but I don’t find myself landing on thinking they’re entirely bad. Time will tell and I’d actually be pretty happy to be proven wrong.
when used in a thoughtful way
The thoughtful way is not at all; sincerely, a very very very tired dev who reviews slop commits daily.
We’re in the same boat, friend. Believe me, I detest the slop as much as you do. However, it is possible to use the LLMs in a way that isn’t miserable for everyone - I’ve been slowly cajoling my coworkers into it. It takes a certain kind of discipline that I haven’t found particularly common from people that just want the robot to “do the thing”.
One of our product people happens to have that discipline. Their PRs are thoughtful and understandable and they take the time to actually understand their changes before slinging them. So, I know it is possible, if rare, currently.
But if the only useful approach is built around discipline alone for a tool that is meant to be used for all, isn’t it, at a group level, a failing proposition?
Anecdotal, but the coworkers I know that have the most discipline and care about their output are the ones that use it the least.
Yeah, also anecdotal, but the ones who use it the most at my job are also the most insufferable and have nothing to say during meetings
My opinion is that there isn’t a one-size-fits-all answer to this question. There exists a class of software for which the detriments of using LLMs in a non-disciplined way is kinda irrelevant. Generally, this is the kind of software that isn’t worth the money that would be spent on an actual developer. These would be, like, very small user-base internal applications.
I might also argue against the “meant to be used for all” part of that statement. That’s the way that AI companies - and many execs - are trying to position LLMs, but I don’t think that’s the reality of their usefulness. Kent Beck did a pretty good talk about this recently that I think summarizes the position well. LLMs let you make mistakes in days that used to take months. The corollary to that is that they also enable you to fix those mistakes in days instead of months, but that requires understanding, thought, and patience.
software quality has been DOWN THE GUTTER on average everywhere even fron teams who try to be thoughtful about it
Absolutely. We’re still figuring all this out and it’s going to take time. I believe that LLMs have a place in the software development lifecycle but where exactly that is depends largely on the project.
For example, I think that open source projects should continue to ban LLM generated code. The barrier to entry and quality of submissions is simply too low for there to be any benefit. Code review, on the other hand, might actually supply some useful findings.
Look at the community name, shill
just moved all my apps over to obtainium. honestly, i think i’m just gonna start minimizing my already fairly low usage of tech.
I switched to ObtainX when obtanium started throwing me connection errors during it’s background checks.
obtainx has even more slop on its repository :( not throwing shade, im using it too.
Inb4 Acquirium fork?
I was about to suggest Komi Store but it’s already infected with Claude code. I don’t have any alternative.
Never heard of this, but at a glance it looks like something that would be quite easy to replicate, even at a basic level of functionality.
