Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

LLM Writing Tropes.md

tropes.fyi

Post reply on HN
Print view View original

111–120 of 211 posts

Re: LLM Writing Tropes.md

#111

Post by capnrefsmmat »

grey-area wrote: post #84
capnrefsmmat wrote: post #15

I work on research studying LLM writing styles, so I am going to have to steal this. I've seen plenty of lists of LLM style features, but this is the first one I noticed that mentions "tapestry", which we found is GPT-4o's second-most-overused word (after "camaraderie", for some reason).[1] We used a set of grammatical features in our initial style comparisons (like present participles, which GPT-4o loved so much tha…

I wonder if th style shift has anything to do with training for conversation (ie. tuning models to respond well in a chat situation)?

Probably. One common feature of LLM output is grammatical features that indicate information density, like nominalizations, longer words, participial clauses, and so on. Perhaps training tasks that involve asking the LLMs for concise explanations or summaries encourage the use of these features to give denser answers.

Re: LLM Writing Tropes.md

#112

Post by orbital-decay »

esperent wrote: post #43
duskwuff wrote: post #33

Earlier quoted context omitted.

IIRC, it's well documented that negative instructions tend to be ineffective - possibly through some sort of LLM analogue to the "pink elephant paradox", or simply because the language models are unable to recognize clichés until they've already been generated.

That was definitely true with early LLMs but I don't know if that's still the case. Certainly not as strong as it used to be. I think now most negative instructions are followed quite well but there's still a few things that must be deeply embedded from pretaining that are harder to avoid - these specific annoying phrasings, for example.

Both pink elephant effect and accuracy drop on negative instructions are pretty fundamental biases for both humans and LLMs. It impossible to get rid of them entirely, only mitigate them to an acceptable degree. Empirically, the only way to make a model reliable at harder negative instructions is CoT, especially a self-reflection type CoT (write a reply, verify its correctness, output a fixed version). If the native CoT fails to notice the thing that needs to be verified and you don't have the custom one or a verification loop, you're out of luck.

Re: LLM Writing Tropes.md

#113

Post by grey-area »

sebastiennight wrote: post #86
grey-area wrote: post #81

Earlier quoted context omitted.

At this point it’s pretty easy to detect unaltered LLM output because it is such bad writing. That will change over time with training I would hope. At some point I imagine it will be hard to tell. I honestly don’t know what sites like this will do when that happens and the only way of detecting LLMs is that they are subtly wrong or post too much, we’d be overrun with them. Not sure if we should be hopefully or fearf…

I wouldn't say it's "bad writing", but rather that the sheer volume of it allows the attentive reader to quickly identify the tropes and get bored of them. Similar to how you can watch one fantastic western/vampire/zombie/disaster/superhero movie and love it, but once Hollywood has decided that this specific style is what brings in the money, they flood the zone with westerns, or superhero movies or whatever, and the…

It is objectively bad writing:

Overly focussed on style over content

Melodrama even when discussing the mundane

Attention grabbing tricks like binary opposites overused constantly

Overuse of adjectives and adverbs in particularly inappropriate places.

Lack of coherence if you’re generating large bits of text

General dull tone and lack of actual content in spite of the tricks above

Re your assertion at the end - sure if I didn’t know I’d think it was a particularly stupid, melodramatic human who didn’t ever get to the point and probably avoid their writing at all costs.

Re: LLM Writing Tropes.md

#114

Post by rrvsh »

lucumo wrote: post #68
matusp wrote: post #60

I tried using Gemini for some light historical research. It could not stop using tech metaphors. Lords were the CEOs of their time, pope was the most important influencer, vassal uprisings were job interviews, etc. The metaphors were almost comically useless and imprecise, and Gemini kept using them even when I explicitly asked it to not do that.

I think that's Gemini trying to personalize the answer specifically for you. It really leans heavily into that to the point of being galling. You can give it additional instructions in the settings, but you have to be careful with that too. I've put my tech stack and code preferences in there to get better code examples. A while later I asked it about binary executable formats and it started ending every answer with…

Even Gemini 2.5 was extremely snarky. I basically disable all guardrails via prompts and instructions, and it started getting snippy at me for apparently acting like a know-it-all.

Re: LLM Writing Tropes.md

#115

Post by samrus »

Its so sad that perfectly fine patterns of writing are now associated with slop. Just because corporate greed couldnt stop themselves from making a bubble they then had to shove down our throats to prevent popping

Re: LLM Writing Tropes.md

#117

Post by Terretta »

malfist wrote: post #38
Jordan-117 wrote: post #10

Wikipedia also has an exhaustive guide, though it's not fun finding tropes you use yourself (I'm very guilty of the false range "from X to Y" thing): https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing Another one that seems impossible for LLMs to avoid: breaking article into a title and a subtitle, separated by a colon. Even if you explicitly tell it not to, it'll do it.

Thats the thing about AI writing though. Those tropes are things humans do too. But like once or twice in an article. Not every single freaking paragraph

Perhaps the problem is SEO for persuasive writing, LinkedIn-spiration for “business” writing, and school papers for research. The machines read a lot more of this than you would. So for them human writing would appear overwhelmingly troped. Whatever works, right?

Re: LLM Writing Tropes.md

#118

Post by grey-area »

lucumo wrote: post #85
grey-area wrote: post #81

Earlier quoted context omitted.

At this point it’s pretty easy to detect unaltered LLM output because it is such bad writing. That will change over time with training I would hope. At some point I imagine it will be hard to tell. I honestly don’t know what sites like this will do when that happens and the only way of detecting LLMs is that they are subtly wrong or post too much, we’d be overrun with them. Not sure if we should be hopefully or fearf…

> At this point it’s pretty easy to detect unaltered LLM output because it is such bad writing. And yet people seem to still be terrible at that. Someone uses an em-dash and there's always a moron calling it out as AI. > I honestly don’t know what sites like this will do when that happens and the only way of detecting LLMs is that they are subtly wrong or post too much, we’d be overrun with them. My personal take is…

Never seen this in the wild, but that sounds unfortunate about em-dashses.

Personally, I think it will matter deeply if sites like this are overrun by bots. If you believe your description, why are you here?

Re: LLM Writing Tropes.md

#119

Post by networked »

capnrefsmmat wrote: post #110
networked wrote: post #19

Earlier quoted context omitted.

You may be interested in my links on AI's writing style: https://dbohdan.com/ai-writing-style . I've just added your preprint and tropes.fyi. It has "hydrogen jukeboxes: on the crammed poetics of 'creative writing' LLMs" by nostalgebraist ( https://www.tumblr.com/nostalgebraist/778041178124926976/hyd... ), which features an example with "tapestry". > Why is the instruction tuning pushing such a noticeable style shift…

Thanks for the links. You may be interested in the other LLM writing style studies I've been collecting: https://www.refsmmat.com/notebooks/llm-style.html

You're welcome, and thanks. I've added a link to your notebook to my page.
Post reply on HN