Comment by scythmic_waves
4 hours ago
I also love the visualizations but I'm getting heavy LLM vibes from the prose:
> One setting drives this,...
> The cost is now about the rows you actually touch, not rounds times table size.
Etc.
I get the brain scramblies [1] from trying to parse this writing style at work so I hate to see it elsewhere. Apologies if I'm wrong. But if I'm not then OP don't use an LLM to write for you. It's hazardous to your reader's health [2].
[1]: https://www.youtube.com/watch?v=ipUJq-odt5Q
[2]: https://discourse.haskell.org/t/how-to-keep-enjoying-program...
I noticed some AI tells, but found overall the article not too bad. It did seem to waffle at times though.
> Storing a lake as thousands of 1 MB Parquet files is a bad practice anyway, and 2.0 does not rescue it.
The "does not rescue it". No human would write like that.
> I'll explain what that means on a table you already know.
No I don't already know that table.
Also
> and claims 40x on graph reachability
Is really hard to parse.
The section on recursive CTEs wasn't well written and didn't explain how the optimisation was done. This article explains how the recursive CTEs were improved https://duckdb.org/2026/08/25/how-duckdb-runs-recursive-ctes...
> The "does not rescue it". No human would write like that.
This is what I don’t understand. Supposedly LLMs are trained on human text. Why do they come up with such unrealistic prose? Is it intentional because the companies want the tells to be obvious?
They’re not just trained on human prose. They’re sent to RLHF, and also their language changes as a result of RL on verifiable rewards.
Getting it to write well is really hard because there’s no real way to verify whether it’s good prose or not. You and I can tell, but we can’t write a verifier that codifies our judgment.
Maybe they’ll find a way to improve this, but for now it’s certainly one of the harder problems to solve for LLMs.
Part of it is that I think they also have poor theory of mind, which I imagine is also a hard thing to train it to do.
1 reply →
> The "does not rescue it". No human would write like that.
On the contrary. It is unnatural for a native speaker, which I don't think the author is. For someone that speaks English as a second language, it is not uncommon to use expressions literally translated from their first language, which may be understandable but weird for native speakers.
Hilarious that even DuckDB's article has many of LLM tells as well
I've lost count recently of how many times Claude has given me something in this style that I can't understand, and then I ask it to rework parts of it, and then it tells me that the original things it claimed weren't actually quite right anyway.
I'm starting to read it as a sign of low LLM effort not just low human effort. It seems most common when one few-sentence prompt leads it to generate 4+ paragraphs (and the longer the output, the worse the odds). Prompting to dig into each resulting paragraph one by one, to make them readable, makes it do higher-effort deep dives.
It really is unreadable. I guess you're supposed to skim an AI summary. Too bad you'd never see the visualizations that way.
I wonder how much the prevalence LLMlish is causing a shift in normal meatbag's writing style as well?
I definitely add LLMisms to my speech to other techies as ironic jokes, but I've noticed more than once it creeps in naturally. I'm starting to embrace my typos as the few lingering signs of my humanity...
I may be in the minority but I didn't get LLM vibes from this. Not enough to be bothered by it, at least
I have tried out the alpha releases of 2.0 and I got slopcoded vibes from it.
> It's hazardous to your reader's health [2].
Just because some guy on some forum said that doesn't make it true. That's not how you establish facts regarding health claims.
The entire internet is like a wikipedia talk page now. If you say it is true often enough it becomes self evident.
Not that i question that reading mostly ai slop for long enough makes you feel dead inside.
[flagged]
[flagged]
Where were the facts invalidated? Why can't a reader despise a writing style that LLMs converge towards?
I think you're right on your last point, btw, nobody will care and we'll be the poorer for it. Just like how McDonald's and Walmart have driven out and undercut localized taste and culture in the US, so it shall be with writing of all kinds. It's happening right now and readers are getting used to reading the intellectual equivalent of a Big Mac.
3 replies →
At what point did I "invalidate facts"?
3 replies →
This sounds to me a lot like mass hysteria, people reading other people's behaviour online and reproducing it unconsciously.
More and more really important and useful information will arrive like this for us to consume. There's no way around. So this is a disservice for newcomers that could come and go unscathed but instead is crippled by these kinds of comments that brings nothing of substance to the table and has the potential to make them hate something they otherwise wouldn't even notice.
Also, from https://news.ycombinator.com/newsguidelines.html:
Curious how you see low-effort writing as a "shallow dismissal" or "tangential"
Everything is low-effort writing if your judgement is ideologically charged. Just read the damn post, it's very good, there's nothing low effort, but you need to read it as one single piece, not dissect it looking for hints of LLMisms, killing the article in the process.
Also if you think LLMisms so bad it's spam, you also don't get a free pass. From the guidelines:
3 replies →
Look at the specific AI habits called out in this comment: https://news.ycombinator.com/item?id=50037220
This sort of writing decreases readability. People say "just have your own LLM rewrite it" like you don't lose value when you go from prompt -> slop you didn't review enough to clean this crap up in -> someone else's prompt to change the style -> finally someone reads it.
Do you know what happens a double-digit percentage of the time when I ask Claude to rewrite some shit that it gives me like this? It says things like: "I overstated this, I rechecked and actually..." or "this claim doesn't hold up, actually [this other thing is true]..."
So it's a sign that the claims in the post likely weren't vetted very hard.
So if you aren't proofreading I'm gonna be skeptical. And saying "deal with it" doesn't rescue it. Does it?
And then there's the reflexive "you must just be an ideological hater." No. I'm someone who uses the tools in a domain where quality matters enough that I have to dig into the quality of the tool output and spot the tells for when it's low output, so that I can deliver shit that works reliably and consistently.
This is all absurd discussion. If you disagree with the article style, there is a flag button there.
Our time is better used submitting something useful instead of debating meaningless guesswork in the comments.
My manager was previously whining about something similar when it comes to generated reports and I just pulled down all of his writing and made the LLM write in his style, he is really content now. Do the same using your own writing and you wont have to be offended
So now we need a decoder to be able to read articles. It's true that it's painful to read and it's good to be called out for it