Hacker News Reader

Comment by karim79 | Hacker News Reader

"So, if we publicly shame people whose text looks like it might have been written by a machine – because it mimics the language used for human reasoning – and people stop writing in ways that they internalize as "AI writing" out of fear of false detection, it sends a signal that your language for reasoning must be policed, or you too could be held up to public scrutiny."

This is honestly both terrifying and well articulated.

High praise to the blog author.

View on HN

Last week I read through 10 project proposals by students. Two of those ticked all boxes for LLM writing throughout their full text. Not that I checked for LLM-markers specifically, but if a text makes you go: wait a minute, am I reading the output of an LLM? only to then present you with more markers also content-wise, that will have an impact on the human reading the text.

And it should. If someone sends me an obvious copy-paste mass email it also has an impact on how serious I take that email to be meant as an actionable proposal targeted at me specifically.

If they half-ass their proposal which has to do with language I can reasonably infer they may also half-ass the real world implementation which in this case also had to do with language. If you're unable to describe your own idea on half a page of paper in your own words, maybe the students who are able to do so should be treated fair.

I don't care wheter or not they use LLMs, in fact do. But engage with the ideas and results and convince me you really care about them.

Exactly, without talking about automated checkers or publishing policies, if a text gives readers the impression is was LLM-generated it will affect how they judge it.

Recently a contractor presented a small internal tool they made for a very specific task. The UI text gave a direct impression to be entirely LLM-generated with no human edition. It makes the entire tool look vibe-coded, affecting how we judge it. Now I question whether they even reviewed the functionality correctness, which I wouldn't doubt if the UI didn't look generated.

no its not terrifying. its just raising the level of writing, if you are using not x but y then you fucking better justify the need to use a negation

And when LLMs write ‘better’ according to your standard — as if stating by negating was an issue before — what then?

If other approaches didn’t improve people’s writing you think LLM-shaming… will?

This is honestly a very, very naive statement. We are social animals and we naturally gravitate towards devaluing and shaming certain styles of speech. We police speech already! It’s often unfortunate, but it’s not devoid of function. I, for one, am happy with shaming LLM speech. It’s never been so easy to detect lazy thinking.

What do you think about TFA and its contention that perfectly normal language is being targeted by the AI witch-hunt?

I personally avoid the em dash, but it has been used in writing for a long, long time.

Frankly, when humans produce empty reasoning like sentences with little reason behind them, we should be allowed to call it a slop too.

What about when they produce correct reasoning and express it with language that has superficial similarities to LLM output?

> perfectly normal language

Define "normal language?"

In this instance, language which would have passed a style guide and an editor in 2020 but reads as AI in 2026.

Some could say with how quick one is to judge everyone against the lowest common denominator, that such decision making skills is itself, lazy.

There are plenty of idioms, find a different idiom, tough titties.

Surely it hasn't escaped your notice that the LLMs don't tend to stick to just the one set of idioms/devices. They're constantly running new batches of them into the ground

It's not just "It's not just X; it's Y", it's other stuff too

Congratulations, you've made the meme recursive.

Reply on news.ycombinator.com