[jstanley]

This post exhibits a specific LLM tell that I haven't seen mentioned before. It's the style where inanimate objects or concepts are treated as actors, using verbs as if they were actually the one doing something.

* bias compounds

* variance diffuses

* configs store parameters

* BF16 + RNE (6 bytes) plateaus

* errors repeat

* six bytes match ten

This sort of thing reads really well and conveys the idea in very few words. It's good writing! But in my experience humans don't generally "let nouns verb" as much as LLMs do, maybe we're just not as clever with words.

[ForceBru]

LLM tell? Inanimate objects and concepts are treated as actors all the time: the series converges, the function reaches its maximum, the sun shines, the wind blows, history repeats itself, words rhyme, interest compounds, etc.

What's wrong with "configs store parameters"? I guess "parameters are stored in configs" could be more correct, but IMO it means exactly the same thing and sounds just as natural. "Six bytes match ten" is shorthand for "the performance of the algorithm that uses six bytes of storage matches the performance of the algorithm that uses ten bytes of storage". But here we have "performance matches", which is an inanimate concept doing something, so is this an LLM smell too?

[jstanley]

It's not wrong, I tried to make this clear. It's good. It's just unusual, in my experience, for humans to use that kind of wording.

Yes everyone says the sun shines and the wind blows, those are specific idioms. Noone says bias compounds or variance diffuses or six bytes beat ten.

I'm not saying they shouldn't! They probably should! It's just that LLMs say it much more than humans do.

> "Six bytes match ten" is shorthand for "the performance of the algorithm that uses six bytes of storage matches the performance of the algorithm that uses ten bytes of storage".

Yes, I understand this and support it. I am emphatically not saying it is bad writing. It's an unbelievably brilliant piece of terse writing that most human writers would not stumble upon in the course of writing the post.

[strogonoff]

I recommend to think twice before penalising potential human creativity by saying that a novel to you turn of speech is a sign of LLM use. If you base your judgement on “unusual phrase”, it should be a sign that you are probably unable to tell.

[jstanley]

It's not novel to me! I see it all the time... when talking to LLMs.

[strogonoff]

If you have only seen it in LLM output, then it is clearly novel to you when it comes to actual writing. “Speech” in “this turn of speech is novel to you” is intended to mean human written speech.

I will rephrase: if you see a phrase in human speech that you have not seen used in human speech before, don’t penalise human creativity by saying it came from an LLM.

More specifically, the pattern you continue to latch onto dominates writing and has done so for decades. Right here on HN you can find instances of not merely “inanimate subject + verb” but specifically the phrase “bias compounds” from 5 years ago and beyond.

Other examples in use by humans all the time:

— River overflows

— Camera clicks

— LLM hallucinates

— Engine roars

— Secrets rest

— CD player stutters

— Ecosystem explodes

— Door invites

— Stock dips

— Airplane crashes

Antropomorphisation more generally and metaphor even more generally have existed since forever. Authors have played with form and tried to convey the point in different interesting ways since forever. Do you think Homer vibe-wrote The Odyssey?

Yes, LLM chatbots make it exceedingly easy—and it is one of their societal harms—but please do not discredit creativity by insinuating the author didn’t do the work themselves.

[jstanley]

In all of your examples, a human author would usually prefix with the word "the".

Nobody routinely says the things in your example without some supporting words.

And it's not just presence -- it's density.

And, to be clear: are you making the claim that this post was not LLM-generated or at least LLM-assisted? Or are you merely making the claim that people saying things like "nouns verb" might not be LLMs even though in this case the text is in fact most likely from an LLM?

[thaumasiotes]

> It's not wrong, I tried to make this clear. It's good. It's just unusual, in my experience, for humans to use that kind of wording.

But... it's not unusual in the slightest.

[jstanley]

It's unusual to use it in the way LLMs do, in the extremely terse style where "noun verbs" or "nouns verb" are basically considered sentences all on their own.

[greatgib]

What makes it llm generated to me is that somehow it is hard to read.

What I mean is that each sentence looks well made and from a highly skilled writer. But reading a few parameters I'm lost quite fast. Like if there was no coherence or progression. Just some ideas sometimes even repeated in random order even if in the end there is point/explanation to be made.

Like when Claude or another llm drops you a 5 pages block of text or MD spec that is totally unreadable even if it is supposed to make sense.

I think that it is unusual for human generated speech because usually if you have good with words and to do great sentences, you will also to do it in logical and coherent way at the multiple paragraphs level too. Or at the opposite, if you don't know how to redact proper paragraphs, you will. It not be able to do great sentences anyway.

[imtringued]

This poetic form of writing "reads well", but it completely failed to convey the idea to me. I had to read the blog multiple times to get the point, because poems are not meant to be direct, unambiguous or simple to understand.

From a technical writing perspective, this is a terrible blog post.

Here is a better blog: https://cloud.google.com/blog/topics/developers-practitioner...

[0xDEAFBEAD]

The maximally concise formulation is not always maximally understandable.

[moralestapia]

https://news.ycombinator.com/item?id=48284979

>housing appreciating

>stocks appreciating

Are you an LLM?

[jstanley]

I was prepared for you to have found examples of me using this pattern (in fact I think better examples are in the comment you replied to, "reads well", and "this post exhibits").

But I don't think the examples you chose are very good. It's not "stocks appreciating", it's "$1m in stocks appreciating at 9%". The stocks are not an actor in that sentence. "$1m in stocks" is a thing that is having appreciation done to it.

If I had written a self-contained clause saying "stocks appreciate", that would have been a good example. But that's not what I wrote.

[Asraelite]

> "$1m in stocks" is a thing that is having appreciation done to it.

How? "appreciate" in this sense is not a transitive verb. There cannot be an agent.

In any case, I don't think you need to defend this. It's not about humans never using that pattern, it's about how frequent it is relative to LLMs. Individual counterexamples do not disprove a trend.

[moralestapia]

Is "$1m in stocks" an inanimate object or a concept?

[jstanley]

It's not being used as an actor in the sentence.

[moralestapia]

"$1m in housing appreciating at 3%"

Which one is the actor there?

Help me learn, ESL.

[thaumasiotes]

> Help me learn, ESL.

There's nothing to learn from jstanley; he's a crackpot.

The subject of "appreciating" is "$1m in housing", or if you want to narrow it down as much as you can, the subject is the word "dollars". ("$1m in housing" is shorthand for "one million dollars in housing".)

[jstanley]

Noone is the actor there, that's the passive voice.

[fragmede]

Was this written by an LLM?

[jstanley]

Which part? My comment? No. The post we're commenting on? I think pretty obviously it was at least LLM-assisted. That's not to knock the technical content, and not even (necessarily) any more a criticism than if I said I thought the author had used spellcheck.

[simianwords]

pangram says 100% ai generated

[rcxdude]

Anthropomorphism simplifies!