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

How to stop Claude from saying load-bearing

jola.dev

Post reply on HN
Print view View original

11–20 of 650 posts

Re: How to stop Claude from saying load-bearing

#11

Post by pocketarc »

In the olden days, I enjoyed Opus 3 because it was easy to have it sound way more human than GPT.

Nowadays, with the focus on agentic use and coding, it seems models have all been RLHF’d to death, it’s so incredibly hard to have them write in a different voice than their default. I put together a skill to review its writing and have it edit its own output (e.g. code comments), which does make a difference, but isn’t perfect.

What, if anything, do people do for writing? That feels like a neglected side of LLMs. They’ll make 100 Bash calls referencing ancient commands without batting an eye but heaven forbid they use something other than “load-bearing” while talking. For something trained on “all the human knowledge” it’s incredible how limited their default vocabulary seems to be.

Re: How to stop Claude from saying load-bearing

#15

Post by p-e-w »

pocketarc wrote: post #11

In the olden days, I enjoyed Opus 3 because it was easy to have it sound way more human than GPT. Nowadays, with the focus on agentic use and coding, it seems models have all been RLHF’d to death, it’s so incredibly hard to have them write in a different voice than their default. I put together a skill to review its writing and have it edit its own output (e.g. code comments), which does make a difference, but isn’t…

> Nowadays, with the focus on agentic use and coding, it seems models have all been RLHF’d to death

I don’t get it. If nobody likes this writing style, how can it be the result of human feedback? Something else is going on.

Re: How to stop Claude from saying load-bearing

#16

Post by lostlogin »

pugio wrote: post #8
pugio wrote: post #6

I wrote a thing about exactly this, but I'm resistant to blogging for undefined reasons so, maybe this will help someone... # AI speech is an Infohazard Apart from all its other possible boons and ills, one danger of AI is just that it is useful, so you use it. A lot. In earlier days I would dive deeply into an author's work and start to think and write like them for a while. It was a heady feeling: slinging sonnets…

References: Information hazard: https://en.wikipedia.org/wiki/Information_hazard Babel: https://en.wikipedia.org/wiki/Tower_of_Babel On the Calculation of Volume: https://en.wikipedia.org/wiki/On_the_Calculation_of_Volume The revenge of NLP The tool uses good old-fashioned regex/NLP—no LLMs—and rewrites the visible LLM Markdown without touching files on disk. I made it by analysing 10M+ words of past pi transcripts,…

> Babel: https://en.wikipedia.org/wiki/Tower_of_Babel

I was hoping for a reference to the Babel Fish, whispering its translations in your ear.

Re: How to stop Claude from saying load-bearing

#17

Post by postalcoder »

pocketarc wrote: post #11

In the olden days, I enjoyed Opus 3 because it was easy to have it sound way more human than GPT. Nowadays, with the focus on agentic use and coding, it seems models have all been RLHF’d to death, it’s so incredibly hard to have them write in a different voice than their default. I put together a skill to review its writing and have it edit its own output (e.g. code comments), which does make a difference, but isn’t…

It's why I like Gemini 3.1 Pro. That it sounds much more human than other LLMs is testament to Google's inability to post train.

gemini-2.5-pro-experimental was the GOAT, though. It was an emotional wreck, down in the dumps and feeling terrible for itself after failing to patch a file several times. Very amusing to read, all the while watching it make a mess of my codebase.

Re: How to stop Claude from saying load-bearing

#19

Post by boofus »

pocketarc wrote: post #11

In the olden days, I enjoyed Opus 3 because it was easy to have it sound way more human than GPT. Nowadays, with the focus on agentic use and coding, it seems models have all been RLHF’d to death, it’s so incredibly hard to have them write in a different voice than their default. I put together a skill to review its writing and have it edit its own output (e.g. code comments), which does make a difference, but isn’t…

Good. I don't want LLMs sounding human. I want the ability to shame and discredit anyone passing the job of prose to a machine. There's an art to writing, and hopefully LLMs never truly get it right.
Post reply on HN