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

121–130 of 211 posts

Re: LLM Writing Tropes.md

#121

Post by Terretta »

mosselman wrote: post #89

I feel like the audience of the file is more for me the reader rather than the LLM. > Add this file to your AI assistant's system prompt or context to help it avoid common AI writing patterns. So if I put this into my LLM's conversation it is like I am instructing it to put this into its AI assistant's system prompt, so the AI assistant's AI assistant. The alternative is to say: "Here is a list of common AI tropes fo…

The source doc and the gist name dozens of specific bad patterns by label (“Negative Parallelism,” “Gerund Fragment Litany,” etc.) and repeat examples of them.

An LLM guide would do better to avoid every one of those labels and examples, since the whole point is not to prime the pattern.

Instead each instruction should describe the positive shape of good writing – what a well-constructed sentence, paragraph, or piece actually looks like.

Following this line, here is Claude rewriting OP:

https://gist.github.com/abuisman/05c766310cae4725914cd414639...

// This post’s typography and Oxford commas by human hands.

Re: LLM Writing Tropes.md

#123

Post by Terretta »

twoodfin wrote: post #98

Great list. The one that grates most for me not on this list is aggressive use of first-person-plural and second-person perspective: “We’ve all been there.” “Your first instinct might be…” “Now you have a…”

ChatGPT 5.2+ has gotten aggressive about attributing its errors to its interlocutors.

User: "This code gave this error."

GPT: "That's because you did X wrong. Do Y."

User: "You gave me X. And Y is wrong."

GPT: "Honestly, that's great feedback on X. Your Y is broken because Z."

Re: LLM Writing Tropes.md

#124

Post by adonovan »

One annoying trope I keep seeing in Gemini output is the punchy invented concept name in a tripartite list:

- “The Pledge”:…

- “The Turn”:…

- “The Prestige”:…

(For this particular example I used real terms from the stage magic world, at least according to Christopher Nolan’s film, as it captures the same meaningless-to-the-uninitiated quality.)

Re: LLM Writing Tropes.md

#126

Post by Terretta »

stratos123 wrote: post #106
ilitirit wrote: post #62

Can someone explain why LLM's write like this when most humans don't?

Base models don't write like that. This appears during RLHF. It's not totally clear why*, but probably a large part of the answer is that this style looks great to human reviewers, and only starts looking terrible once you get to play around with the released model and realise it talks like that all the time . * The technical term is "mode collapse", see [1][2] [1] https://en.wikipedia.org/wiki/Mode_collapse [2] http…

> This appears during RLHF. It's not totally clear why…

Imagine a world (ha) where everyone writing on LinkedIn from cafes and couches starts disrupting AI by opting into rating ChatGPT responses.

How might that turn out?

Re: LLM Writing Tropes.md

#127

Post by Terretta »

bitwize wrote: post #9

You know how no one ever wrote their own software and then generative AI came along and suddenly we could have app meals home-cooked by barefoot developers? (The use of such cottagecore terminology for a process that requires being an ongoing client of a hundred-gigabuck, planet-burning megacorporation rubs me in many wrong ways.) If AI finally gets rid of the thing that drove me nuts for years : "leverage" as a verb…

> now people might actually believe me

“Leverage” feeling “impacted” much?

Re: LLM Writing Tropes.md

#128

Post by matricks »

lelanthran wrote: post #104
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…

> That will change over time with training I would hope. There's precious little training material left that isn't generated by LLMs themselves. Consider this to be model collapse (i.e. we might be at the best SOTA possible with the approach we use today - any further training is going to degrade it).

> There's precious little training material left that isn't generated by LLMs themselves.

Percentage-wise this is quite exaggerated.

> Consider this to be model collapse (i.e. we might be at the best SOTA possible with the approach we use today - any further training is going to degrade it).

You consider this above factor to lead to model collapse? You’ve only mentioned one factor here; this isn’t enough. I’m aware of the GIGO factor, yes. Still there are at least ~5 other key factors needed to make a halfway decent scaling prediction.

It is worth mentioning one outside view here: any one human technology tends to advance as long as there are incentives and/or enthusiasts that push it. I don’t usually bet against motivated humans eventually getting somewhere, provided they aren’t trying to exceed the actual laws of physics. There are bets I find interesting: future scenarios, rates of change, technological interactions, and new discoveries.

Here are two predictions I have high uncertainty about. First, the transformer as an architectural construct will NOT be tossed out within the next five years because something better at the same level is found. Second, SoTA AI performance advances probably due to better fine-tuning training methods, hybrid architectures, and agent workflows.

Re: LLM Writing Tropes.md

#129

Post by pmg101 »

Sometimes the elements in the `Avoid patterns like:` list are quoted text it should avoid, sometimes they're just descriptions of things to avoid. But they are "quoted" in both cases which is a bit confusing. Maybe not to an AI though.

Re: LLM Writing Tropes.md

#130

Post by jval43 »

Kye wrote: post #94
lucumo wrote: post #68

Earlier quoted context omitted.

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…

The new memory feature in Gemini got turned on by default and every answer came out like this. It kept working in details from one particularly long thread. Everything was framed in terms of the common elements. Everything. I turned it off immediately.

How can you turn it off without turning off history ("My Activity") altogether?

I noticed the "memory" too and it's turned Gemini into a useless syncophant for me, but so subtle that I almost didn't spot it.

Post reply on HN