Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Stop Slopware

stopslopware.net

Post reply on HN
Print view View original

161–170 of 171 posts

Re: Stop Slopware

#161

Post by magnitudes »

JackSlateur wrote: post #143
magnitudes wrote: post #30

I find these really are not only condescending but also really miss the mark and ironically come off as really uneducated in my opinion, and that really is the most infuriating type of condescension. What you call slopware today is becoming less and less sloppy every six months as new coding models drop. In 2 years the “unmaintainable mess” is going to be far better and far more maintainable than anything the enginee…

That is your belief, not a fact It has been years since "new models will perform less sloppy code, in 6 months" Current code is still dumb as hell. The emoticons is the part that works really well.

Opus 4.5 is not better and less sloppy by an order of magnitude than sonnet 3.7? Amazing how people can’t look at what’s happening right in front of them

Re: Stop Slopware

#162

Post by Larrikin »

danielbln wrote: post #101
Larrikin wrote: post #10

Why would any actual software engineer be against slopware? When it inevitably all comes crashing down because there was no actual software architecture or understanding of the code, someone will have to come in to make the actual product. Hopefully by then we will have realistic expectations for the LLM, have skilled up, and we as a community treat them as just another feature in the IDE.

This just reads as copium to me. "Those hacks vomiting out slop.. pah, when they call me, the artisan, in to clean up their mess in a way God intended, then they'll see!" More realistic: AI assisted tooling will continue to improve as it has, the average code quality will rise as conventions and workflows improve and those who wait to be called in to clean up slop or whatever will wait forever, pushed by the wayside…

I think you decided what my point was before reading my entire comment.

Re: Stop Slopware

#163

Post by tavavex »

square_usual wrote: post #98
avian wrote: post #92

Earlier quoted context omitted.

You mean the cook who will in the same unendingly patient and helpful manner sometimes confidently suggest putting glue into your dishes and serving your guests rocks for lunch?

I'm sure these year-old examples of errors from a bad product are still valid!

What bad product? I'm not as categorical as OP, but acting like this is a solved problem is weird. LLMs being capable of generating nonsensical stuff isn't a one-off blip on the radar in one product that was quickly patched out, it's nigh unavoidable due to their probabilistic nature, likely until there's another breakthrough in that field. As far as I know, there's no LLM that will universally refuse to try outputting something it doesn't "know" - instead outputting a response that feels correct but is gibberish. Or even one that wouldn't have rare slip-ups even in known territory.

Re: Stop Slopware

#164

Post by JackSlateur »

magnitudes wrote: post #161
JackSlateur wrote: post #143

Earlier quoted context omitted.

That is your belief, not a fact It has been years since "new models will perform less sloppy code, in 6 months" Current code is still dumb as hell. The emoticons is the part that works really well.

Opus 4.5 is not better and less sloppy by an order of magnitude than sonnet 3.7? Amazing how people can’t look at what’s happening right in front of them

Where is the code ? No code ? Only "just see what is right in front of you" and slop ?

Re: Stop Slopware

#165

Post by casey2 »

The only way to stop slopware is to write "good software" that solves the problem. Proponents of "good software" are usually terrible at solving problems, and will fight tooth and nail against the idea that there even is a problem.

God forbid experienced developers experience pain? What are you talking about? Experienced FOSS devs deserve eternal hellfire. Or rather, they already live in a self-imposed hell.

Re: Stop Slopware

#166

Post by casey2 »

Larrikin wrote: post #10

Why would any actual software engineer be against slopware? When it inevitably all comes crashing down because there was no actual software architecture or understanding of the code, someone will have to come in to make the actual product. Hopefully by then we will have realistic expectations for the LLM, have skilled up, and we as a community treat them as just another feature in the IDE.

Because open source "devs" can't make an actual product. LLMs are there direct competition, both competing for user attention.

The idea that code gluers understand the code better than a chatbot (that admittedly totally lacks the ability to understand) isn't clear.

Just like an LLM they can only create very ill-thought-out ripoffs of software from the 70s and 80s (they have yet to reach the level of ripping off 90s Microsoft.)

Re: Stop Slopware

#167

Post by cadamsdotcom »

Low effort projects don’t stand the test of time. The high quality ones always win out eventually.

There’s lots of creation going on right now thanks to agentic coding & vibe coding - but also lots of abandonment. It’s easy to confuse “lots of stuff is being tried right now” with “overall quality of software is going down”. But one does not lead to the other.

Even if it did, it’d still be exciting. Given a choice I’ll take a vibrant jungle where many ideas are being explored. That’s way more exciting to me than some kind of beautiful garden in which there is no room available for anything new or weird.

Re: Stop Slopware

#168

Post by dormento »

danielbln wrote: post #111
cesarb wrote: post #104

Earlier quoted context omitted.

> will wait forever, pushed by the wayside by those who can deliver great quality with the help of these new tools. That sounded a lot like the "have fun staying poor" argument from the peak cryptocurrency days.

Did it? Cryptocurrency enabled gambling and illicit purchases, that's it. In all other ways it was/is a solution in need for a problem. Current gen AI has a ton of issues, but it nevertheless enables vast amounts of use cases today, right now. And hoping that slop that is created today will provide work for the artisanal craftsman in the future is wishful thinking at best.

When you think about it, "vibe coding" kinda enables gambling, but with software.

You set up your prompt, CLAUDE.MD, include the source files and let it rip. It gets some things right, some things wrong. You fix some things manually, /clean and go again. Sometimes you gotta throw it out and start over. Feels like "most players stop just before striking it big".

Re: Stop Slopware

#169

Post by dormento »

i_love_retros wrote: post #106

I'm not sure if I am just losing my mind at this point, but all this slop everywhere is starting to be funny. I honest to god am in teams chats at work with high up the food chain architects and leaders (and plain old devs) and people are pasting chatgpt responses either as evidence backing up their claims of how something should be done, or as an actual response to another person as if they typed it themselves. I ha…

Same here. I'm torn between "feels bad being the only sane person in an otherwise insane environment" and "I have enough self-awareness to realize I cannot be the only sane person here".

Re: Stop Slopware

#170

Post by mccoyb »

smolder wrote: post #154
mccoyb wrote: post #89

Earlier quoted context omitted.

No, you weren't clear, nor are you correct: you shared FUD about something it seems you have not tried, because testing your claims with a recent agentic system would dispel them. I've had great success teaching Claude Code use DSLs I've created in my research. Trivially, it has never seen exactly these DSLs before -- yet it has correctly created complex programs using those DSLs, and indeed -- they work! Have you ha…

This is desperate rebuttal from ignorance. My point stands. You haven't innovated, you've just leaned on an LLM to work with your unoriginal DSL. I'm sure it's worth 100 megawatt-hours.

I see -- unoriginal, but it was accepted for publication at a leading programming languages venue?

Do some experiments, stop speaking out of your ass.

Post reply on HN