I sort of think the whole middlebrow angst thread about Bourdieu going on right now applies to LLM writing
LLM Writing Tropes.md
31–40 of 211 posts
Re: LLM Writing Tropes.md
#32If only we could fix how it writes like garbage
Re: LLM Writing Tropes.md
#33Weirdly, LLMs seem to break with these instructions. They simply ignore them, almost as if the pretraining/RL weights are so heavy, no amount of system prompting can override it
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.
Re: LLM Writing Tropes.md
#34If this bugs you, open chatGPT personality settings, choose “efficient” base style, and turn off the enthusiasm and warmth sliders
It makes a tremendous difference. Almost everything on this list is the emotional fluff ChatGPT injects to simulate a personality.
Re: LLM Writing Tropes.md
#35As the article points out at the end, these aren't bad per se. The issue is that LLMs overuse them, and we're all getting the same(-ish) LLM. It's not so different from how people sometimes have their idiosyncratic phrasings they use all the time.
Re: LLM Writing Tropes.md
#36Re: LLM Writing Tropes.md
#37No mention of Claude/ChatGPT's favourite new word genuine and friends? They also like using real and honest when giving advice. Far as I can tell this is a new-ish change. > Honestly? We should address X first. It's a genuine issue and we've found a real bug here. Honorable mention: "no ". I guess this helps reassure adherence to the prompt? I see that one all the time in vibe coded PRs.
Similarly, "X that actually works"
...and half of the time still doesn't do what you want.
Re: LLM Writing Tropes.md
#38Wikipedia 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
Re: LLM Writing Tropes.md
#39If this bugs you, open chatGPT personality settings, choose “efficient” base style, and turn off the enthusiasm and warmth sliders It makes a tremendous difference. Almost everything on this list is the emotional fluff ChatGPT injects to simulate a personality.
[flagged]
Re: LLM Writing Tropes.md
#40Trope -> Snowclone