Hacker News Reader

Comment by pech0rin | Hacker News Reader

I feel like I’m starting to have my own psychosis where if I read a blog article and I get a whiff of AI smell my brain turns off and I can’t read anymore.

I’m not blaming the author maybe this is their original idea and its edited by AI but I physically can’t keep reading it. AI blindness or something.

View on HN

Same with youtube lately. You can hear the AI cadence and phrasing in the scripts even when it is read by a human

Don't generally mind AI-isms but somehow the cadence is really irritating when spoken.

>It's not X it's Y

Yeah, I really hate this. The clippy short little sentences that clearly aren't someone's actual thought process.

Same here. I realized for me it boils down to a combination of mutual respect + return on time investment. You write your text yourself = there is a guarantee you have at least read it = an implicit social proof of value. Take this guarantee away, and there is not much incentive left for me to invest even 5 minutes of own time into your blog post, fellow stranger on the internet.

Even without AI, if someone with 1M followers posts something, why would even 10% of followers bother reading it? That's more time invested by the readers than the writer. Even if a film has a very high budget and a lot of time was invested into it, is it still worth your time to watch it?

I think they are saying the author spent more time writing it than you personally reading it. In this analogy a film took a year to make and 2 hours for you to watch it.

I think it's because LLMs write things down that normal people wouldn't - they go the extra mile, but the reader isn't interested in the extra mile.

Which is an interesting development. I think a lot of people have gotten impatient with long form, high density content thanks to years of rapid fire short bursts of internet - comments, tweets, shortened or clip-edited videos and podcasts (removing all the natural quiet points, especially at the end of sentences so you get theseChopped sentences wherePeople talk likeThis so that youDon't hear any naturalBreaks in aSentence).

Having an LLM now have the relative superpower of reading everything with the same amount of detail and attention, and write something in response to it + filling in the blanks is a bit of a shock.

It has all of the attention to detail and none of the context.

So if you decide to spend your time on reading it, you end up reading a lot of total nonsense that could be technically true only if you lacked any sort of bigger picture and decided to make up your own.

YES me too. I powered through this particular blog post, but... man.

Even when I know that some content MIGHT be useful for me, I still can't read it.

One blog post closer to the dead internet, and we don't browse the web directly but read it to through an ai lens.

Sergey fried our brains teaching us how he avoids frying his own brain.

Agreed. These days my subconscious mind is looking for telltale signs of AI slop (the emdash being one such example), and certain phrases ("... does the heavy lifting" , "... comes the part that matters the most ...", etc.) and the moment the number of alerts crosses a (low) threshold, I'll close out the tab and forget about the content.

Sure, the idea behind the blog post may have been good, but if you have to use AI to flesh it out, it's no longer of interest to me.

"The page is only a viewer — git is the record."

Claude writes like Billy Madison preparing a book report. "The puppy became a dog—but the industry... that, my friends, became a revolution."

Yes. AI;DR.

I’m to the point where, with few exceptions:

1. If I’m writing something for human consumption (including my future self), I will write it by hand

2. I will only read an LLM’s output if I’m the one who prompted it

If you can’t be bothered to take the time to write it, why should I take the time to read it?

(And I say this as someone who routinely maxes out the $100/month claude subscription)

I'd like my colleague - who submitted 19 LLM generated markdown files for review - to submit the prompt for review instead of the output. That's the human part, the rest is just LLM generated word vomit listing all the implementation details. These might be important for another LLM to write the implementation, or to use as inspiration to split up the task into subtasks for humans, but it's not for me. Humans wouldn't go into that much detail speccing out software.

Might as well call it "spam psychosis" when you stop reading a spam email as soon as you realize what it is.

It's unhealthy to read garbage and it's good that you know it.

Pangram says the beginning and end were human, but the middle was ai.

Am I the only one who uses AI for everything except writing?

I feel like it's still terrible at writing good prose, and I'm not even talking about fiction. But it's good at pretty much everything else.

I feel like the point of writing isn't the output, but to get your own thoughts in order. But perhaps that's just me writing for (effectively) myself, and not an audience.

A lot of people don’t use LLMs for anything.

Which is wild to think of given how much and I others around me use it. Its literally doing more than half of my job that I did a year ago, freeing up so much time for more focused work.

I had a peer do this and I saw no change in focus or productivity. They were very sure they were more productive.

Or maybe it's just as good at writing as everything else, only writing is your strength, so you're more discerning with those results? I have suspected some kind of AI Gell-Mann for a while.

I have similar thoughts about how it writes and I'm at best an average writer.

On the plus side, I'm reading more "old" (> 10 year) books than ever.

Reply on news.ycombinator.com