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

71–80 of 312 posts

Re: Various LLM Smells

#71

Post by devin »

tptacek wrote: post #50

The LLM writing sameness is bad. Use LLMs to help your writing! But don't include a word they generate, even just a vocabulary adjustment, in your own output. Have them critique structure and flow, spot overused words and passive constructions and dumb picks for topic sentences. It's great for that, and those are all objective improvements in your writing that won't mess up your style. The LLM sameness in web design…

Absolutely agree. I recently wrote a speech and can't imagine how terribly hack it would have been had I taken the LLM's words as my own. I have second hand embarrassment just thinking about someone writing something important for or about a loved one and using the saccharine crap that was suggested at various points to me. Absolute drivel and a giant flag that you don't actually care enough about the audience to bring your own words.

Re: Various LLM Smells

#72

Post by ryandrake »

dvt wrote: post #49
xienze wrote: post #34

Earlier quoted context omitted.

Tell me your thoughts on the quality of LLM-generated code. I've never understood this attitude where people are absolutely disgusted by the slightest whiff of AI prose but will happily slurp up AI-generated code by the bucketful and proudly proclaim that it's OK because it's better than the average developer can produce.

The key difference is that code is not the end product, but writing is itself the product. (No one's doing "vibe-product-management" for example.) Tbh, I still think code can have a beauty and elegance to it (like a logical proof can, or like a mathematical theorem can), but there's a difference between the two and I'm way less forgiving of AI writing than I am of AI code, especially considering most code (by line co…

> The key difference is that code is not the end product

I think this is open to debate. To me, the code has always been the goal, and the fact that writing it sometimes serves to produce a product is important to others (and what brings the paychecks in), but ultimately not something I've ever been excited about or interested in throughout my career. So I judge a developer based on the beauty and quality of the code he produces, just as I judge an LLM by the same sorts of things.

The fact that AI can one-shot a working CRUD app is not really that interesting to me. If it could make the code beautiful, concise, maintainable, extensible, minimal, performant, readable, and bug-free: a work of art and love that a craftsman would be proud of... that would impress me.

Re: Various LLM Smells

#73

Post by kybernetikos »

ryandrake wrote: post #66
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.

> 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…

I think there are some factors beyond just skill too - the kinds of tasks you're giving the AI, and how involved you are in ensuring the output is good (via either extensive planning guidance, extensive review/testing, or a combination).

Re: Various LLM Smells

#74

Post by danielodievich »

exe34 wrote: post #15
danielodievich wrote: post #3

All of those are included in the bulk of the documents passing my work input these days. It is infuriating. Out of principle I maintain 100% me in all my writing but I don't know if it matters. Well maybe it does... an interviewee recently complimented me on the "nicest and most human resume" they saw recently. That felt good

Do you send your resume to people before you interview them?

I meant interviewer. Sorry!

Re: Various LLM Smells

#75

Post by viccis »

One Python one I hate is that it adds crazy amounts of newlines for no real readability gains.

Instead of this:

  def add_three_ints(x: int, y: int, z: int) -> int:  
      return x + y + z
it will write:

  def add_three_ints(  
      x: int,  
      y: int,  
      x: int,  
  ):  
      return x + y + z
While it's always preferable to do this when you get either long or complex function signatures, Opus 4.7 and GPT 5.5 do this everywhere. When you combine it with their penchant for writing helper functions for everything, you get a ton of vertical padding that messes up the readability imo because Python really relies on your eye seeing indents for scope.

Re: Various LLM Smells

#76

Post by throwatdem12311 »

dvt wrote: post #6

It's kind of interesting how genuinely hard it is to get models to deviate from basically all of these tropes. You can straight up tell it "I hate that card design, do something different, get creative!" and it'll do something either (a) ugly as sin (clearly just essentially a random walk through parameters) or (b) some same-y derivation of that card. In coding, I've noticed a few tropes as well: everything is a "con…

I’d rather they not deviate so I know right away that I can stop reading something because it’s slop.

Re: Various LLM Smells

#77

Post by gchamonlive »

dvt wrote: post #70
gchamonlive wrote: post #55

Earlier quoted context omitted.

> Honestly, I can't fathom thinking that LLM writing is even remotely passable. People that think this should honestly read more. How do you think the author of the page would read this? That sounded pretty asshole-like for me. If it's not for you I'm really sorry for you, you must have to endure really screwed up people.

Maybe you're right and I was a bit too snarky, apologies to the author if he/she was offended. Writing anything implies some vulnerability, and criticism should be constructive.

I know, and we've all been there. It's comfortable to criticize, only when I had a very divisive publication hit front page that I've seen how hurtful dismissive or sarcastic comments can be (https://news.ycombinator.com/item?id=45277346)

And sorry about your blog :/ didn't know it was hacked. Looking at the comment section of the hello world though it gets pretty obvious LOL. You should consider removing it from your HN about though.

Re: Various LLM Smells

#78

Post by tempest_ »

ryandrake wrote: post #66
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.

> 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…

It isnt though.

The industry largely has selected for camp 1 long ago.

If you don't get immediate negative feedback camp 1 can go quite a ways before problems surface.

Re: Various LLM Smells

#79

Post by dvt »

ryandrake wrote: post #72
dvt wrote: post #49

Earlier quoted context omitted.

The key difference is that code is not the end product, but writing is itself the product. (No one's doing "vibe-product-management" for example.) Tbh, I still think code can have a beauty and elegance to it (like a logical proof can, or like a mathematical theorem can), but there's a difference between the two and I'm way less forgiving of AI writing than I am of AI code, especially considering most code (by line co…

> The key difference is that code is not the end product I think this is open to debate. To me, the code has always been the goal, and the fact that writing it sometimes serves to produce a product is important to others (and what brings the paychecks in), but ultimately not something I've ever been excited about or interested in throughout my career. So I judge a developer based on the beauty and quality of the code…

Imo, this is like saying "I judge a carpenter based on how straight they can cut a piece of plywood." Or like saying "I judge an artist on how accurately they can draw a circle by hand."

I mean that's certainly one way of looking at it, and both can be impressive technical feats. But most people judge carpenters and artists on their end products, their overall vision, their motifs, their philosophy, and so on. On the other hand, as a trained logician, I definitely see proofs (which, by the Curry–Howard isomorphism, are computer programs) have some degree of beauty-within-themselves, but that's quite hard to achieve. Not everyone is a Gödel, after all.

I also think programming languages, despite being Turing complete (which is frankly not saying much), are far too limiting to truly construct magnificent things with.

Re: Various LLM Smells

#80

Post by avador »

devin wrote: post #65
xtracto wrote: post #48

Earlier quoted context omitted.

Someone way more eloquent than me should write a column titled "Why do we read?" Way back in the past (around 30 years ago) I remember reading an article on "how to read a book" or a similar subject. They argued that, you should not skip the acknowledgments, preface and other "personal" related sections of a book, because it was there where you got a glimpse of the person that was writing the book. The idea being tha…

It's not "Why do we read?" but something related that is coming up a lot in my thinking lately is Walter J. Ong's "Writing is a Technology that Restructures Human Thought".

Isn’t “Writing is a Technology that Restructures Human Thought” another way of saying that “feedback has an effect”?

If so, this seems to be a trivial (still worthy) assertion.

For example, I intend to, say, construct a shed. I make mistakes that I only see because I actually constructed. I revise future endeavours involving sheds.

I admit to not having read this piece, and am merely reacting to the title.

—-

Okay, I got through the first paragraph of Walter’s writings. While I nod to the bitterness (I assent to the existence of it), I do not bow.

Post reply on HN