Hacker News Reader

Comment by chmod775 | Hacker News Reader

> LLMs average human writing thats out there

Not really, and also they do not vary their writing like humans would. Human writers do not repeat the same pattern over and over as much as LLMs do. They'd get bored of their own writing.

People as a whole are always going to be sick of whichever affectation current popular LLMs have, since they'd be reading a fair bit of that. As a writer you should steer clear of things that would elicit groans in a contemporary audience and "LLM prose" is just the latest addition.

So, as the person you're replying to said, you'll have to get used to this being a new angle from which writing is critiqued. You'll live happier if you don't let your cortisol spike over it. If it is any comfort, writers will eventually adjust and you'll encounter less of it.

View on HN

Interesting. I agree that it seems that LLMs are wont to fall into recognisable patterns much more readily than humans however I asked a model to evaluate your comment history and it found loads of patterns such as:

“I’m not sure…” / “I don’t…” hedges before disagreement Negation followed by correction/reframing is a recurring structure: essentially “It’s not X, it’s Y”.

And dozens of other examples. I wonder if LLMs really are more liable for it or if it simply seems that way purely because when you use a model it's almost as if you're speaking to the same "person". I think that human language is naturally formed by common agreed meanings of words first, and then phrases.

And in your estimation, is the LLM correct in qualifying that as a pattern, or is it full of shit?

I could ask an LLM to generate something arguing against whatever yours put out, but I won't. I come here to talk to other people, not their electronic sycophants.

Any given person will have phrases or ways of organizing things that they tend towards. But that isn't the same thing. Those patterns are the exception with lots of variance all around them. LLMs lack the same general variance while also going beyond merely favoring a few patterns to the point where you could describe it more as a production line stamping them out. They're also remarkably inefficient with their prose. I think I'm pretty bad on a first pass (see this comment I'm typing right now) but they put me to shame by a huge margin.

> I asked a model to evaluate your comment history and it found loads of patterns such as

> “I’m not sure…” / “I don’t…” hedges before disagreement Negation followed by correction/reframing is a recurring structure: essentially “It’s not X, it’s Y”.

I did a manual human dig through GP's profile and I don't see any evidence supporting this. The literal strings "I'm not sure" and "I don't" do appear a lot (also in replies, which I'm hoping your LLM was intelligent enough to exclude?), and they are used to hedge before making a statement, but not a single one of them even approaches the "It's not X, it's Y" thing your LLM has claimed they do.

Your LLM did not find dozens of examples, it told you it did and you didn't even bother to check.

What you wrote becomes completely incorrect if non-native speaker picks up the pen (like half of folks here, including me). Then you can easily start seeing this stuff and having these... non-smart reactions to manually written comments.

> As a writer you should steer clear of things that would elicit groans in a contemporary audience and "LLM prose" is just the latest addition.

Nope, thats you and your own self-pressures to adhere and conform to imaginary critical crowd, don't push it nor expect it form others. Its not a really happy way to live like that, is it. Maybe a warm fuzzy feeling when being in similar crowd, just pointing out that crowd may be more vocal but its actually pretty small.

Its really just some form of OCD/anxiety, unhealthy competitiveness, with a pinch of pettiness (as you write you completely reject any form of more moderate or tolerant approach or understanding how wrong in your assumptions you may be). You do you, just don't expect much respect for the n-th same comment on x-th article.

You could have read at least read some of my comments on here to quickly figure out I care about pleasing approximately nobody. Your sibling comment at least had their LLM go over them.

If you wish to continue the psychoanalyst LARP, feel free. Rather than be offended, myself and mine are bound to be further entertained.

Reply on news.ycombinator.com