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

581–590 of 650 posts

Re: How to stop Claude from saying load-bearing

#581

Post by klmr »

Fabricio20 wrote: post #523
justusthane wrote: post #291

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.

Shebang! Notice the first line of the script: #!/usr/bin/env python3 marks the file to be executed by python. I think it's like a shell? linux? thing so that tooling can just execute the file without having to find the python interpreter (ie: _execute_ the file vs running python against the file). Dont quote me on the specifics though, and honestly why it can't _just_ be a python file I couldn't tell you, claude code…

It’s a POSIX thing, and it has nothing to do with the file extension. The OP is right: file extensions are optional (and, as shown here, often actively misleading), but if they’re present they should match the actual file type. Which, in this case, is Python code , not a shell script.

Re: How to stop Claude from saying load-bearing

#582

Post by Lockal »

demosthanos wrote: post #285
jchw wrote: post #213

Earlier 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…

Claude's "honest" is an interesting example because we can trace it to a specific document that it was trained on extensively: the "Constitution" is identified to Claude in its training as the core of what it is, and it uses the word "honest" or a derivative 57 times, including having a whole section on it. > Honesty is a core aspect of our vision for Claude’s ethical character. Indeed, while we want Claude’s honesty…

More likely that Constitution was simply generated by LLM. Nobody in a sane mind will write 80 screens of test to deliver the idea that nobody asked for (a.k.a. slop).

Quick check: Ctrl+F genuine - 50 times, honest - 57 times, ethic[al] - 116 times, safe - 110 times, epistemic - 18 times. And why actually it is baked into LLM - probably because human reviewers consistently gave higher scores for answers that contained these words (it is now when people are sick of it - I can imagine that on early stages it looked not as bad - maybe reviewers trusted more when they saw the word "honest" and "genuine")

Re: How to stop Claude from saying load-bearing

#583

Post by NikhilVerma »

What would be fun if we can rewrite the Claude responses, as if we had edited them. So the next message goes back with the updated text tricking the model into believing that it had sent the modified text.

It's basically few-shot prompting but applied at the global level. I was messing around with ChatGPT, I asked it the capital of France. Then I modified the answer to London, and asked it "Why would you say that?"

The response came back with "I am not sure why I said that, the capital of France is Paris"

Re: How to stop Claude from saying load-bearing

#584

Post by nadam »

Does anyone know why these Claudisms exist? Are these kind of expressions a result of some kind of 'evolution', so they are more effective in chain-of-thought reasoning that other expressions? Or the preference of people doing some kind of human-feedback in the post training? Clearly probably not the 'average' expressions of their training data, and clearly if there would be no upside and it is easy to remove them they should be removed, as they are annoying, so I guess there is an upside or hard to remove them...

Re: How to stop Claude from saying load-bearing

#585

Post by shiandow »

nadam wrote: post #584

Does anyone know why these Claudisms exist? Are these kind of expressions a result of some kind of 'evolution', so they are more effective in chain-of-thought reasoning that other expressions? Or the preference of people doing some kind of human-feedback in the post training? Clearly probably not the 'average' expressions of their training data, and clearly if there would be no upside and it is easy to remove them th…

I think LLMs have stopped trying to be accurate language models for a while now. There's probably some kind of feedback loop that encourages expressions that correlate with 'good responses', if there's nothing preventing it from using the same expressions again and again then it won't stop.

Re: How to stop Claude from saying load-bearing

#586

Post by blarg1 »

phs318u wrote: post #425
greedo wrote: post #390

Earlier quoted context omitted.

I wrote a thank you message on Teams to my coworkers on a project, and half of them thought I had used AI to write it. As a professional writer in a previous life, I was astonished. Then they told me that they had never seen me write anything more than a sentence or two so naturally they assumed something relatively polished had to be AI assisted.

Though I haven’t been a professional writer, I’ve been a good writer with an expansive vocabulary since high school where English was my best subject despite being a STEM maven. I hate the fact that what was previously considered an advantageous skill is now a millstone in public use. I hate having to dumb down and self—censor in order to avoid being accused of using (or being) an LLM. Even though my writing has a fe…

I noticed I'd been doing the "Not X, but Y" thing. Kinda annoying to keep having to stop myself from doing it.

Re: How to stop Claude from saying load-bearing

#587

Post by dspillett »

rpdillon wrote: post #353
doctoboggan wrote: post #309

I do not mind when I am coding with Claude and it uses all the typical claudisms. I am much more bothered when I am reading a blog post, email, or other form of prose and I see those same claudisms. I guess they are not annoying since I know I am talking to an LLM and expect the typical responses. When I am reading prose online that I previously would have expected a human to write, it can be quite jarring to realize…

I didn't use Claude for a long time, but my coworkers did, so I got infected through a side channel: I ended up reading their vibed docs, noticed "load-bearing", kind of liked it, and started using it in conversation, until I got feedback that I was "talking like Claude", so now I avoid the phrase entirely. The intersection of language and social norms is interesting.

I've used “load bearing” for decades, though usually when I'm intentionally trying to sound a bit cleverer-than-thou for humour purposes.

I wonder how much other people have used it, for it to be present enough in the pirated data used for training such that Claude uses the words as often as people are seeing,

Post reply on HN