This is a minor nit, but why is OP's script a Python script with a .sh extension? I know the extension doesn't "matter", but if I see a .sh extension I'm expecting a Bash script.
How to stop Claude from saying load-bearing
291–300 of 650 posts
Re: How to stop Claude from saying load-bearing
#292Lots of people have their own voice and tend to prefer certain phrases. This has been the case for a long time and is generally not a big issue. Now LLMs come along and they also have their own phrasing preferences. But now it's a problem because what used to be personal preferences of a single person that manifests in 5000 words per day from one person tops, is now the bias of a single model multiplied x10,000,000,0…
An interesting solution would be for these AI companies to train a few different versions of these models, all with different speech characteristics. Then, when you start a conversation, you get a random version.
They can't, because they use RL with synthetic data and LLMs as judges. So the system naturally convergences towards certain load bearing, genuine, not just annoying but ridiculous verbal tics.
It's probably the reason most LLMs share the same tics across labs, because they cross train and distil each other's models on an industrial scale. You also can't escape it in generated text that's already online. So if, say ChatGPT first had some random idiosyncrasies, it then contaminated the entire AI ecosystem.
Re: How to stop Claude from saying load-bearing
#293Earlier quoted context omitted.
I think it might be even worse. LLMs seem to get tragically stuck on certain patterns. Maybe it's partly because a pile of weights essentially always starts from scratch in the same condition, but even within a single conversation, it will literally just latch onto words and repeat them incessantly, to the point where it becomes annoying. So for example, current Claude models love "honest". They are always producing…
use the wrong phrasing and suddenly you can create your own word of the day for an AI model. I have a delightful time poisoning my company's AI system this way. I invented my own word that sounds perfectly cromulent† to an ordinary person, and any brain that's read a book learns how to infer meaning from context, so it's not a problem. When I get a e-mail response from a coworker using my special word incorrectly, th…
I don't see how you can tell it's AI, instead of just your co-workers having no respect for language. See: management-speak using "double-click".
Re: How to stop Claude from saying load-bearing
#294This is a minor nit, but why is OP's script a Python script with a .sh extension? I know the extension doesn't "matter", but if I see a .sh extension I'm expecting a Bash script.
Cause it was written by AI?
Re: How to stop Claude from saying load-bearing
#295Lots of people have their own voice and tend to prefer certain phrases. This has been the case for a long time and is generally not a big issue. Now LLMs come along and they also have their own phrasing preferences. But now it's a problem because what used to be personal preferences of a single person that manifests in 5000 words per day from one person tops, is now the bias of a single model multiplied x10,000,000,0…
I think it might be even worse. LLMs seem to get tragically stuck on certain patterns. Maybe it's partly because a pile of weights essentially always starts from scratch in the same condition, but even within a single conversation, it will literally just latch onto words and repeat them incessantly, to the point where it becomes annoying. So for example, current Claude models love "honest". They are always producing…
> LLMs seem to get tragically stuck on certain patterns.
That is likely an artifact of the fine-tuning process:
> Once a style tic is rewarded, later training can spread or reinforce it elsewhere, especially if those outputs are reused in supervised fine-tuning or preference data.
> That creates a feedback loop:
> * Some rewarded examples contain a distinctive lexical tic.
> * The tic appears more often in rollouts.
> * Model-generated rollouts are used for supervised fine-tuning (SFT).
> * The model gets even more comfortable producing the tic.
Re: How to stop Claude from saying load-bearing
#296Lots of people have their own voice and tend to prefer certain phrases. This has been the case for a long time and is generally not a big issue. Now LLMs come along and they also have their own phrasing preferences. But now it's a problem because what used to be personal preferences of a single person that manifests in 5000 words per day from one person tops, is now the bias of a single model multiplied x10,000,000,0…
> But now it's a problem because what used to be personal preferences of a single person that manifests in 5000 words per day from one person tops, is now the bias of a single model multiplied x10,000,000,000 generated tokens per day so any bias sticks out like a sore thumb.
I am more pessimistic than that. Soon enough even people will start talking like LLMs. After listening to 5000 words per day, especially growing up, getting "help" with the homework, kids will start talking like LLMs.
- "Did you eat the cookies, Jimmy?"
- "You're absolutely right to question me, father. In fact I did eat all the cookies. But it's not a load-bearing issue. My honest take is we can go to the store and buy more".
Re: How to stop Claude from saying load-bearing
#297I mourn the removal of Claude's Concise Style. I'd provide it a roughly drafted paragraph, ask concise-Claude to "rewrite for clarity", out comes the same paragraph, but cleaned up and perfect for grant writing. BTW, this approach also tends to prevent certain phrases like "load-bearing", because it is working directly with something I wrote first. It also still says what I wanted to write (not writing the science fo…
At the top of Claude.md put a few lines where two "people" ask and answer a couple of questions. Very tersely.
Re: How to stop Claude from saying load-bearing
#298Lots of people have their own voice and tend to prefer certain phrases. This has been the case for a long time and is generally not a big issue. Now LLMs come along and they also have their own phrasing preferences. But now it's a problem because what used to be personal preferences of a single person that manifests in 5000 words per day from one person tops, is now the bias of a single model multiplied x10,000,000,0…
> But now it's a problem because what used to be personal preferences of a single person that manifests in 5000 words per day from one person tops, is now the bias of a single model multiplied x10,000,000,000 generated tokens per day so any bias sticks out like a sore thumb. I am more pessimistic than that. Soon enough even people will start talking like LLMs. After listening to 5000 words per day, especially growing…
> "You're absolutely right to question me, father — in fact, I did eat all the cookies. But it's not a load-bearing issue — my honest take is simple: we go to the store and buy more."
FTFY
Re: How to stop Claude from saying load-bearing
#299Earlier quoted context omitted.
And the word "suspenders" in British English means what Americans would call a garter belt, hence it sounding particularly odd over here.
That is what I had in mind. I was also wondering what American call them so thanks for answering that.
Americans call bum bags fanny packs. Always raises a smile.
Re: How to stop Claude from saying load-bearing
#300Earlier quoted context omitted.
‘Landed’ and ‘honest’ are also words it seems to overuse.
Claude is obsessed with making things land. More than once I've reminded it that it's not a pilot.
It’s a common metaphor for merging a branch to the trunk. Probably because multiple in-flight development branches create a sort of air traffic control problem.