What “great games?” Even independently of the advent of LLMs, the game industry has been in the doldrums for decades. AI adoption might be new, but it hasn’t exactly reversed that trend yet
I'm not sure how widespread this meme (in the general sense, not the internet fad sense) is, but I came across it theorized by this humanities account, Adam Walker - Close Reading Poetry:
Perhaps, but the examples in that article all clearly look like they're using AI-generated art assets. You might as well call that style "slop" in the sense that it is very easy to spot. I don't know if it's possible to create a general AI filter for the actual code, but certainly labelling ones that had AI-made visual and audio assets, with minimal human craftsmanship involved, would be a good first step.
I think this is really an excellent comment because it challenges us to reframe what we take for granted as creativity, enforces us to reconsider what creativity could be in the face of really powerful automation.
What you and I are saying is synonymous. I’m simply reusing language that the post I’m responding to used. And also de-glamorizing/de-romanticizing things a bit, sure.
And given that fast food is the pinnacle of sustenance as a product and Hollywood has been content-brained since 1977, sure!
Obviously entrusting an entity to do everything is different from using a dependency or library, but aren’t LLMs for work just a natural progression of this? Programming is about automation. Programmers have been automating and outsourcing their work since the concept of
SDKs were invented. Or even since high-level languages were invented. The industry was already doing this, and doing it excessively, long before Claude. left-pad happened a decade ago and we’ve learned nothing.
Not really. Even with left-pad there was still some skilled work required. At this point my wife could vibe code an app or a website and it would be actually quite good - not the slop of 6 months ago.
Writing left-pad isn't the issue, the issue is that projects were importing a one-liner package and blindly using it, which requires no skill.
> Second, even if the package’s logic is correct, I can’t help but be amazed by the fact that developers are taking on dependencies for single line functions that they should be able to write with their eyes closed. In my opinion, if you cannot write a left-pad, is-positive-integer, or isArray function in 5 minutes flat (including the time you spend Googling), then you don’t actually know how to code. Hell, any of these would make a great code screening interview question to determine whether or not a candidate can code.
> Finally, stringing APIs together and calling it programming doesn’t make it programming. It’s some crazy form of dependency hacking that involves the cloud, over-engineering things, and complexity far beyond what’s actually needed.
Obviously LLMs make the situation even more dire, but I think people are overlooking that the industry was automating itself out of programming as a craft even before them. It's just the automation involved reuse of the work of other humans.
Sorry but there's no way that assembling libraries - even stupid ones like left-pad (which I'll note was an extreme example) - is in no way comparable to just saying "Claude make this program for me", which is pretty much where we are now. My wife can do the latter but not the former.
This isn't just "a bit more automation". It's "now we don't need lift operators".
Of course, prompting an LLM to one-shot an app is a quantum leap in comparison, but c'mon, the whole direction of the field is towards automation, abstraction, convenience. It's always trended letting the programmer write less code. Have to deal with less menial tasks. So LLMs are just the latest manifestation of that motivation. And, perhaps in a decade or two, something will come along to replace LLMs, and this conversation will happen again, except even with more desperation and despair.
But while your example exists, I don't believe that's how the industry works, yet. They're not just allowing laymen to one-shot their production software. Certainly some teams may be trying that, and some indie devs have made good money already selling vibecoded software. But I don't think the technology is good enough to auto-generate professional code at scale, without human oversight. Give it another eighteen months.
Yeah, but therein lies the difference between coding as a hobby and software engineering as a profession. The latter tends to promote DRY overuse of dependencies, whether the dependencies were invented in-house or not!
I don’t deny that there’s more slop than ever, but I would argue that this is a quantitative issue not a qualitative one, because frankly, the Internet has been drowned in slop for over a decade now. Those creative industries have had to deal with a lot of low quality content (some bot-generated even before LLMs!) for a while now.
So the central challenge has always been the same: discoverability is the difficulty. It’s just even harder now, and we need to find ways to promote the good stuff.
You people don't care about human mastery or excellence at all. So what if we produce more stuff cheaper and faster? That wasn't the problem. We're making it harder for people to get rewarded for genuine effort and dedication and in exchange for alienating us from our work we get a lot of lower quality crap. It sucks!
This is the kind of argument people make about furniture vs ikea and human made watches. This is not mastery, its just hobby/art. Human excellence is in abundance, not in raw dogging the most artistic Java class.
You could've made the same argument at any time in history because all technologies do the same thing. Things will go on, mastery will remain.
I'm not just talking about programming. If you want to give up doing your job to Anthropic and OpenAI, that's your business, just get the hell out of other fields that weren't asking for your help.
It doesn't make all people's lives worse. It makes those people's lives worse that think their job (now redundant) was an artistic endeavour. The rest of the world gets cheaper things at affordable prices.
Except that the remaining jobs are the ones people hate. They're also the low earning jobs -- high earning jobs are the ones that are being downsized.
Investors I know are investing on the prediction that people will be less able to participate in the profitable parts of the economy in the future, and most transactions will be between businesses.
We're building a future for humanity where people are both unhappier and poorer.
Given the amount of complaints and generally downtrending tone on HN over the past decade and a half, did people really enjoy programming for work? It feels like the vicissitudes of the market, from the “move fast and break stuff and technical debt be damned” era of ZIRP, to “move even faster because now companies have to show profit and we are post-ZIRP cracked 100x engineers” just led to a lot of sloppy inelegant code, features and products built that never shipped, and unending meetings about half-baked business requirements. And a lot of the programming just ended up writing API glue code.
If you’re a The Art of Computer Programming-reading, code golf-competing, blogging neat elegant hacks kind of programmer, were you really getting that experience coding at work?
Work always comes with bullshit. Its the nature of the thing. I don't think anyone was really getting code golf-style experiences at work, but they likely had enough positives that they outweighed the negatives, which resulted in net "enjoying" work. For a lot of people, AI removed a lot of the positives and left a lot of negatives, and some are still coping with that in one way or another.
reply