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

Various LLM Smells

shvbsle.in

Post reply on HN
Print view View original

191–200 of 312 posts

Re: Various LLM Smells

#191

Post by LoganDark »

overgard wrote: post #184
onion2k wrote: post #85

Earlier quoted context omitted.

Well, I have bad news for camp 1.. It's bad if they work in a part of the industry where code quality or efficiency matters. That's maybe 10% of the total though.

I think it matters everywhere -- just because some fields get away with making trash doesn't mean that they're not vulnerable to people taking their lunch by making something distinctly-not-trash. People put up with a lot when there's lock-in, but there's a breaking point. (I say now using a linux desktop about 90% of the time now because windows has become such a fucking disaster)

Being vulnerable makes money unfortunately. And making money now has always been seen as more important than being sustainable in the long-term. Even if an exploit later takes away every cent of earnings.

Re: Various LLM Smells

#192

Post by ulrikrasmussen »

adamdb wrote: post #94
sofixa wrote: post #82

Earlier quoted context omitted.

> The LLM sameness in web design is good. Most sites shouldn't try to be idiosyncratic. The best design for a site with real utility is legibility, and LLMs are better at that than the median developer. Always laying out the same buttons? Always using the same type scales? Good! If it looks good to you, you weren't going to do better on your own, and you were very likely to do worse. See, I disagree. Having seen plen…

I'm going to play devil's advocate, who cares if it all looks generally the same? I grew up before everyone had dial-up, and I remember back then, when Web surfing on Netscape Navigator, all the websites also had a similar structure. Homogeneity in this context, to me, signals a design system that works best in the moment.

Uniqueness is a costly signal in a sea of information that is all calling for your attention. It signals that you as an author have spent real time on your web page to make it yours.

Re: Various LLM Smells

#193

Post by userbinator »

Planktonne wrote: post #8

> The LLM generated writing obviously felt significantly better than my own writing. A general pattern for LLMs is that they look really good at things you are bad at. What that means is that if you find yourself thinking of its output as significantly better than yours in a particular domain, there's a high chance that you are not equipped to judge that quality effectively.

That's because LLM output is "average"; so if you're below, it will obviously look better than what you can do, and vice-versa. It will be interesting to see what happens when current LLM output becomes the bottom, as everyone worse has pulled themselves up to that level.

Re: Various LLM Smells

#195

Post by Scryptonite »

I personally wonder if the writing (and coding) smells are being leveraged for watermarking/steganography. Like, if it's quirky but intentional; they're biding the time, leaving breadcrumbs so they can more effectively sift new internet content, or perhaps tracing/de-anonymizing.

I can also see how it is not necessarily the case, since all models seem plagued by having unique cliche patterns. We all seem to experience the writing smells from the same models. I see 'cleanly' a lot less from GPT 5.5 vs <5.4

Re: Various LLM Smells

#198

Post by left-struck »

Barbing wrote: post #47
GrinningFool wrote: post #27

Earlier quoted context omitted.

Jab, jab, thrust is how I think about that pattern. Or tap tap whack, if you prefer. And it shows up for for positives too: "Smooth. Effortless. A perfect fit for your needs". In any style of informal or persuasive writing this shows up , as if it has to drive the point in. I kind of wish we'd stop talking openly about what the tells are. It's nice to be able to determine with fair accuracy - but it couldn't last for…

> I kind of wish we'd stop talking openly about what the tells are. Least this way it’s out in the open perhaps, since enough users have training enabled labs will naturally learn what annoys us. Had the same thought though

Yeah, I think in this case, pointing out what’s obviously llm is genuinely useful since it will lead to more diversity in websites and a better tool. I mean I don’t usually care if a website is LLM generated as long as the copy is human written

Re: Various LLM Smells

#199

Post by akomtu »

That's an interesting difference between true intelligence and its LLM imitation. If you throw a pile of mediocre data at LLM, its level will drop to mediocrity, for it can't discern true from false, good from bad. However if you throw the same data at an expert human, he will ignore it, and maybe pick a few bits of novel knowledge, so overall his level will raise a bit.

Re: Various LLM Smells

#200

Post by yuye »

overgard wrote: post #181
ryandrake wrote: post #66

Earlier quoted context omitted.

> A general pattern for LLMs is that they look really good at things you are bad at. This is true for coding, too, which I think, to a large degree, might explain the polarized differences in opinions on HN about the quality of LLM-produced code. You have the 1. "AI produces code better than I could possibly write, one shots things it would take me days to do, and has made me 10X more productive!" camp, and you have…

Yup, pretty much. The hard part too is it's not like you can just learn the basics and be able to tell good code apart from bad -- the more you learn to code, the more intricate your understanding of good code is. It's like becoming a good writer; just knowing grammar and spelling doesn't make your writing interesting. Not to mention that there's just a lot of bad advice out there that you can't recognize as bad advi…

>I think looking at an LLM code and thinking you're now a coder is like watching a someone play guitar and think you can just pick up a guitar and play a song. The truth is, if you want to be good, you have to do the work.

So many posts here on HN claiming they created another useful tool with AI.

No, you didn't create it. AI did. You only had a supporting role. You're Ringo Starr and the AI is John Lennon.

Post reply on HN