LLMs Are Complicated Now • Hacker News Board

Re: LLMs Are Complicated Now

#21

Post by jghn » Sat, Jun 20, 2026, 1:47 PM UTC

ekidd wrote: post #14

lproven wrote: post #5

Earlier quoted context omitted.

[[citation needed]] I am a professional writer and have been for over 30 years. (I do not use any form of LLM ever.) This means I read a lot . This also means that I have 30+ years of experience of readers not understanding what I wrote, or not getting further than the title, or not getting the main message, or inverting it in their heads, or inserting their own message and then complaining when I diverge, and an end…

Claude's writing style is at least as distinctive as any human's personal style. It has a long list of favorite words, verbal tics and common structures. On top of that, LLM writing is often bad in a very particular way: it's weak on actual things to say, but with an overheated style. Some days, I spend over 4 hours a day reading walls of text written by Claude. If I couldn't recognize Claude's default "voice" by now…

I often run my writing through scans for AI tells. The number of things it flags that are just my own personal vocal tics, that I've had for 40+ years, is amazing.

In other words, correlation != causation

Re: LLMs Are Complicated Now

#22

Post by jghn » Sat, Jun 20, 2026, 1:49 PM UTC

roenxi wrote: post #19

ekidd wrote: post #14

Earlier quoted context omitted.

Claude's writing style is at least as distinctive as any human's personal style. It has a long list of favorite words, verbal tics and common structures. On top of that, LLM writing is often bad in a very particular way: it's weak on actual things to say, but with an overheated style. Some days, I spend over 4 hours a day reading walls of text written by Claude. If I couldn't recognize Claude's default "voice" by now…

Claude's default voice, yes. But I'd assume a lot of people have learned to prompt it to something other than its default style. IMO it is good practice to have a style guide to feed in with the prompt. > On top of that, LLM writing is often bad in a very particular way: it's weak on actual things to say, but with an overheated style. This point is interesting because it raises the question of what "LLM writing" actu…

One thing I think that helps is that for anything more worthwhile than message board posts like this I use Claude to review my text, make suggestions, and iterate on structure with me. But I'm the one writing the bulk of the text. I'll take some of its suggestions verbatim, but only if I genuinely like it better than anything I came up with myself.

The end product is something much more polished than anything I'd writ eon my own, but still comes off as being genuinely from me. At least that's what people have told me when I've asked.

Re: LLMs Are Complicated Now

#23

Post by jghn » Sat, Jun 20, 2026, 1:50 PM UTC

skydhash wrote: post #11

lproven wrote: post #5

Earlier quoted context omitted.

[[citation needed]] I am a professional writer and have been for over 30 years. (I do not use any form of LLM ever.) This means I read a lot . This also means that I have 30+ years of experience of readers not understanding what I wrote, or not getting further than the title, or not getting the main message, or inverting it in their heads, or inserting their own message and then complaining when I diverge, and an end…

I don’t think TFA is written by AI. But AI written pieces do have a certain feeling. A sort of saccatto in the succession of ideas that does not feel natural. They emphasize certain points, and you as a reader, you just wonder why is that. There is the “This thing, not just that thing”. There are also the three successive propositions (mostly in one sentences) to accentuate an idea and “Negation. Strong positive idea…

Just like em-dashes, some people have always done these though. Why are they penalized with immediate AI slop witch hunts? The LLMs didn't come up with these tics out of thin air.

Re: LLMs Are Complicated Now

#24

Post by ekidd » Sat, Jun 20, 2026, 1:59 PM UTC

mirekrusin wrote: post #17

ekidd wrote: post #14

Earlier quoted context omitted.

Claude's writing style is at least as distinctive as any human's personal style. It has a long list of favorite words, verbal tics and common structures. On top of that, LLM writing is often bad in a very particular way: it's weak on actual things to say, but with an overheated style. Some days, I spend over 4 hours a day reading walls of text written by Claude. If I couldn't recognize Claude's default "voice" by now…

That reply was AI written.

Lol, no. I've always sounded like that, and there are decades of my writing online.

Also, FWIW, Pangram scores my writing as entirely human.

Claude's writing isn't easy to identify because it uses em-dashes and bulleted lists. Claude's distinctive style goes much deeper than that.

Re: LLMs Are Complicated Now

#25

Post by simion314 » Sat, Jun 20, 2026, 2:06 PM UTC

jghn wrote: post #23

skydhash wrote: post #11

Earlier quoted context omitted.

I don’t think TFA is written by AI. But AI written pieces do have a certain feeling. A sort of saccatto in the succession of ideas that does not feel natural. They emphasize certain points, and you as a reader, you just wonder why is that. There is the “This thing, not just that thing”. There are also the three successive propositions (mostly in one sentences) to accentuate an idea and “Negation. Strong positive idea…

Just like em-dashes, some people have always done these though. Why are they penalized with immediate AI slop witch hunts? The LLMs didn't come up with these tics out of thin air.

>The LLMs didn't come up with these tics out of thin air.

LLMs were trained with a lot of synthetic data to transform them from a complete this text into a chatbot, I suspect that this tons of synthetic data that forces the LLM to answer questions into a specific ways also forced them to have this "synthetic/robotic" language. Claude users would have noticed the "belter and suspenders" phrase just started popping out after an update and I am sure is nto because lots of developers used it in their blogs and Anthropic scrapped those blogs in that update.

Re: LLMs Are Complicated Now

#26

Post by dasil003 » Sat, Jun 20, 2026, 2:12 PM UTC

ekidd wrote: post #24

mirekrusin wrote: post #17

Earlier quoted context omitted.

That reply was AI written.

Lol, no. I've always sounded like that, and there are decades of my writing online. Also, FWIW, Pangram scores my writing as entirely human. Claude's writing isn't easy to identify because it uses em-dashes and bulleted lists. Claude's distinctive style goes much deeper than that.

I think it was a joke

Re: LLMs Are Complicated Now

#27

Post by skydhash » Sat, Jun 20, 2026, 2:17 PM UTC

jghn wrote: post #23

skydhash wrote: post #11

Earlier quoted context omitted.

I don’t think TFA is written by AI. But AI written pieces do have a certain feeling. A sort of saccatto in the succession of ideas that does not feel natural. They emphasize certain points, and you as a reader, you just wonder why is that. There is the “This thing, not just that thing”. There are also the three successive propositions (mostly in one sentences) to accentuate an idea and “Negation. Strong positive idea…

Just like em-dashes, some people have always done these though. Why are they penalized with immediate AI slop witch hunts? The LLMs didn't come up with these tics out of thin air.

You have to start with the reason there’s a witch hunt. I love reading. I read books (novels) almost every day and I’m almost always perusing a textbook pr an article for my jobs and my hobbies. The signal/noise for entertainment or information was fairly high, then come LLM tools.

You start to be interested by the title of an article or a book cover, and then you start reading it and it’s just vapor. Nothing tangible to be gained. It’s like buying something expensive and finding out a cheap trinket under the wrapping.

After a couple of times, you will develop a certain kind of heuristics for this kind of texts. It will not be perfect and will have some false positives, but that’s the only way to keep your sanity.

Re: LLMs Are Complicated Now

#28

Post by binary132 » Sat, Jun 20, 2026, 2:19 PM UTC

roenxi wrote: post #19

ekidd wrote: post #14

Earlier quoted context omitted.

Claude's writing style is at least as distinctive as any human's personal style. It has a long list of favorite words, verbal tics and common structures. On top of that, LLM writing is often bad in a very particular way: it's weak on actual things to say, but with an overheated style. Some days, I spend over 4 hours a day reading walls of text written by Claude. If I couldn't recognize Claude's default "voice" by now…

Claude's default voice, yes. But I'd assume a lot of people have learned to prompt it to something other than its default style. IMO it is good practice to have a style guide to feed in with the prompt. > On top of that, LLM writing is often bad in a very particular way: it's weak on actual things to say, but with an overheated style. This point is interesting because it raises the question of what "LLM writing" actu…

I suspect people who think they are getting away with this are far more obvious than they realize.

Re: LLMs Are Complicated Now

#29

Post by jordanb » Sat, Jun 20, 2026, 2:24 PM UTC

It's the bitter-lesson to feature-engineering lifecycle.

When a technique or technology is new people are making massive gains by just applying it to some use case, or gathering more data for training, or giving it more resources.

As time goes on those "bitter lesson" gains start to hit the shallow part of the logistic curve and companies have to start investing more and more effort into engineering for each small, incremental gain.

Re: LLMs Are Complicated Now

#30

Post by embedding-shape » Sat, Jun 20, 2026, 2:41 PM UTC

charcircuit wrote: post #3

Why didn't this author compare Llama 3 with GLM 5.2 (released 1 week ago) which is a more standard attention based LLM? To compare 2 separate families of LLMs and then pointing out that they are different is not a surprising result and detracts from the point the author is trying to make. https://sebastianraschka.com/llm-architecture-gallery/?compa... If you look at it, the diagrams are very similar, but the main dif…

> Why didn't this author compare Llama 3 with GLM 5.2 (released 1 week ago) which is a more standard attention based LLM? To compare 2 separate families of LLMs and then pointing out that they are different is not a surprising result and detracts from the point the author is trying to make.

The entire point of the comparison is that LLMs look vastly different today than before. Comparing more similar LLMs would detract from the point I thought the author was trying to make.