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

121–130 of 312 posts

Re: Various LLM Smells

#121

Post by perching_aix »

thoughtpeddler wrote: post #116

Does anyone else use the 'smells' as a sort of 'game' to ensure you properly go through a given LLM output (of any kind, be it document, presentation, code, etc) and 'make it your own' by eliminating them? I have a high bar for sharing content so I always do a rigorous pass to eliminate the em dashes, the contrastive negations, the 'quietly', and any other extraneous verbosity, and find that it helps me just really t…

This reminds me to a video essay I saw a few months back. Guy explained that one of the metrics he evaluates game quality with, is how much the game manages to hide its game engine.

I think it makes a lot of sense, it's essentially an inversion. Another related thing I recall is hearing game creators talk in terms of "gimmicks" and "scenarios". Anything that gives a structure, a framework to operate within, I'd say is always useful. This is much the same.

Re: Various LLM Smells

#122

Post by soledades »

cortesoft wrote: post #110
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.

So what does this mean in practice, though? Let's say you are correct. You ask an LLM to write something for you, and to you it looks really, really good. So based on your conjecture, that means I am not a very good writer. Ok, but how does that change what I should do? If I am not a very good writer, that means an LLM IS actually better than me, even if it might not be objectively good to an expert writer. My two ch…

Well, no. The LLM is just better than you in a narrow band that appears wider to someone below than above.

From above, or from below with adequate exposure, it feels facile and hollow. It is good at weaving grammatical structures. It is not good at thinking in words in a way that invites a fellow human along for the journey. Because it doesn't think.

Re: Various LLM Smells

#123

Post by OkayPhysicist »

kylemaxwell wrote: post #57

At this point, I want somebody's raw(ish) writing, with spelling errors and grammar mistakes and whatever, at least when it comes to most writing: blog posts, Slack messages, etc. LLMs are great for helping generate ideas, writing code, and maybe even cleaning up some writing, but doing the writing overall? Please don't. I want to hear what you have to say, not what the AI says, if it's something along those lines.

The way I phrase it: If you can't be assed to write it, there is zero reason for anyone to want to read it.

Re: Various LLM Smells

#124

Post by seba_dos1 »

dvt wrote: post #118
seba_dos1 wrote: post #107

Earlier quoted context omitted.

No, it's more like saying "I judge an artist on my terms regardless of how well they sell on the market". > artists on their end products, their overall vision, their motifs, their philosophy, and so on The main output of programmer's work is their understanding of the system they work with, the rest comes from that. Behind the code there's its author's intention, vision, their tastes, philosophy and experience that…

> No, it's more like saying "I judge an artist on my terms regardless of how well they sell on the market". I feel like I need to push back here, because some of the best programmers around: Carmack, Torvalds, Johnathan Blow, even folks that make programming languages like K&R, Rob Pike, etc. are judged on their respective end products, not on minutia found in code reviews. For example, if I asked you "why do you thi…

You're contradicting yourself. First you say that they're judged on the end product, then you mention things that are very clearly not end products but thoughts and visions behind them that only lead to end products.

Frankly, I have no real idea of how good Carmack, Torvalds or Blow are as programmers, I have never worked with them so I don't really have a way to tell (even though I do contribute to Linux and I've seen some of their code). They're likely past a certain above-average threshold, but they haven't got famous for their programming skills.

That said, if you think Torvalds isn't being judged on "minutia found in code reviews", I'm not sure your take is very serious in the first place - that's the main thing he was being judged on for decades now :)

Re: Various LLM Smells

#125

Post by slopinthebag »

bitwize wrote: post #105
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…

Eric S. Raymond has basically stopped writing code by hand altogether. He consistently delivers high quality code without intervening to fix the LLM's output himself, much faster than he would have been able to alone. This is very bad news for camp 2 because it means one of three things: 1) he is extraordinarily lucky 2) he is extraordinary brilliant at manipulating LLMs 3) you really are "holding it wrong" and you a…

4) ESR is in the first group (most likely option)

Re: Various LLM Smells

#127

Post by slopinthebag »

fluidcruft wrote: post #104
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…

There's a third camp between these extremes who is like "goddamn it just type this shit out for me so I don't have to do it myself".

Yes, the third camp and probably the most effective is to do a decent amount of writing yourself and use the LLMs as codegen machines, but where the DSL is natural language. Deepseek v4 flash is an incredible model for this, you can actually get into flow state as you write code and then delegate boring code to the magic autocompletion machine to autocomplete.

Re: Various LLM Smells

#128

Post by timacles »

fluidcruft wrote: post #104
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…

There's a third camp between these extremes who is like "goddamn it just type this shit out for me so I don't have to do it myself".

Definitely the space I'm in, where I know exactly what I need, exactly how to implement it, just saves time typing 100s of lines.

Re: Various LLM Smells

#129

Post by saaaaaam »

Claude is currently and suddenly obsessed with describing anything a little bit involved as being “inside baseball”.

Last month it was quiet things being said out loud.

When you use the tools all the time it’s fun to watch these things pop up a week or so later as normies copy and paste the slop out on LinkedIn and their newsletters.

Re: Various LLM Smells

#130

Post by slopinthebag »

cortesoft wrote: post #110
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.

So what does this mean in practice, though? Let's say you are correct. You ask an LLM to write something for you, and to you it looks really, really good. So based on your conjecture, that means I am not a very good writer. Ok, but how does that change what I should do? If I am not a very good writer, that means an LLM IS actually better than me, even if it might not be objectively good to an expert writer. My two ch…

> My two choices are to keep producing my own crappy writing, or use an LLM to create better (but not great) writing

Are you also an LLM or do you have the capacity to learn and grow?

Post reply on HN