Claude's Load-Bearing Seams | Hacker News Reader

Claude's Load-Bearing Seams

madradavid.com

120 pointsrzk50 comments

The only thing I find funnier than this article is that some people think that LLMs are communicating at a “higher level” than humans and developing some alien language.

The amount of ambiguity is astonishing to me, maybe I’m wrong but there’s just no way that two agents in a clean room wouldn’t devolve into absolute insanity.

Mutually coalescing on a local maximum of abstract concepts over-represented among data distribution weights.

Devolve implies it starts elsewhere

It's like corporate lingo for computers.

The only thing worse than reading the repetitive claude-ism's while using the actual tool is seeing (likely human) efforts to reproduce it on every comment and blog.

I've noticed Claude-ish increasingly creeping into how folks write on HN. It is unfortunate, but not really surprising given how many of the participants in this community are exposed to reams of AI writing on a daily or even hourly basis.

Given the hundreds of thousands I've burned in tokens over the past year, I'm surprised to not have picked up more of that nonsense (AFAICT I haven't :>).

Alternative possibility: Is it that people are using AI to craft their replies? Also yucky.

> Is it that people are using AI to craft their replies?

Very likely at least one person is.

> Alternative possibility: Is it that people are using AI to craft their replies? Also yucky.

Or they have OpenClaw using claude to karma farm, for . . . reasons.

The amount of absolutely bizarre comments you get on here these days is nuts. It always used to be a bit special, but this year is something else.

Yes I’ve noticed AI speak popping up more in verifiably human communications also.

Rather than trust your memory, let me verify that.

> likely human

X to doubt. I think the more parsimonious explanation is that a lot people are lazy and/or uncaring, and given the option to avoid thinking while still producing a vaguely equivalent [1] output they're taking it.

[1] For a loose definition of "equivalent" where they clearly either don't notice the Claudeslop or don't care enough to avoid it, of course.

Oh I am doing it on purpose lately here in HN, and it's hella hard to sound as dumb, repetitive and cliche as Claude.

You are absolutely right, and that's on me.

I think this breaks me out of the actual work I am doing more than anything else Claude does. Every time it tries to offer some mea culpa for a mistake it made, it sounds so ridiculous. Those sorts of responsibility accepting statements are important for humans because there are real emotional entanglements involved in working together. This isn't true with an AI, and when it fakes it, it just confuses the situation more.

I don't mind when Claude says it will make a note of the mistake to avoid it in the future, because that is an actual thing it is doing that might make a difference. But accepting responsibility does nothing, and doesn't mean anything for future interactions.

See the load bearing vocabulary of Claude: https://louisabraham.github.io/load-bearing/

Discussed: https://news.ycombinator.com/item?id=49461817

Haha :/ one of the sad things for me is that prior to LLMs I had a fairly LLMish writing style. Kinda formal, lots of bullet points and em dashes, two instances before etc, etc. since the debut of gpts I've had to adjust my style to be marginally more opaque so that I don't get mistaken for an LLM

Love it (the mockery, that is). So far Opus 5.5 feels noticeably better in this regard (oh, and it’s fast!), but I felt the same about Fable initially. Not buying into the nerfing theories yet but if I find myself going into LLM-tilt again soon then I might join the club.

Opus 5.5 is better but by no means good at writing IMO. Still loves "noun verbs the object" sentences where the verb is an inappropriate and imprecise metaphor. Still loves negating premises nobody previously advocated for. Still loves incorporating irrelevant details of a conversation or investigation into comments and documentation. I don't think I've seen "load-bearing" myself yet but there's still a lot of things landing and being held.

I laughed, and then I cried, and then I laughed again. Bravo. I'm going to go vomit while trying not to choke it up with laughter.

They missed the first legitimate use case for infinite scroll.

It drives me bananas. This post is so triggering.

This is hilarious of course but Opus 5.5 just came out and largely fixed a lot of the Claudlish.

So like, who writes like this and how do we delete them from the training corpus?

At this point, training on public codebases created by "You're Absolutely Right!"-era Claude...

Do we know if it in the training data or if the humans giving rewards in the labs have such awful taste in prose?

It's not the training data. When we've tested the writing style of base models that have not gone through instruction tuning, they're much more human-like (https://arxiv.org/abs/2410.16107). The style shift seems to come from something in the instruction-tuning process, so our current research problem is figuring out what in the process is doing it.

Couldn't get through it, it hurts too much

Good lord, this is several weeks late at this point. The joke is so damn worn out at and I'm personally far more tired of seeing people online thinking they're clever for saying "load-bearing" for the millionth time than I am at Claude doing it. At least it has an excuse.

It's actually several months late as the post was published in July

It would be hilarious if this was generated by a markov chain or something so it would infinitely scroll. Infinite Claude.

Fable 5.1 makes everything a "Rung". These statistical markers are very annoying.

It seems to be that it has a lot of meta analysis studies in its training data

It’s still better than LinkedIn speak. Machines beating us at our own game.

What I want to know is, what would the embodiment of Claudish sound like?

This is totally on you.

I need an audiobook narration of this

LLMs are sophists.

I was disappointed that refreshing the page didn't regenerate the text

I suppose an infinite scroll _would_ be funnier

This is genuinely insightful.

I'm confused - is this meant as satire? The blog author's other posts also look like they are generated by an LLM, so I'm not even sure if the author is trying to be funny or serious?

This entire article is complete AI slop, with the most basic Claudisms present without even needing extensive inspection or needing to use pangram.

I thought HN would be smart enough to not get easily tricked into upvoting such low quality articles like this, but because it mentions "Claude", it is worthy of some intellectual curiosity.

Come on, do better.

EDIT: Of course, unintellectual low quality AI slop posts are allowed on HN. We know that for sure.

straight over the head

…and it was flagged into irrelevance for being pure slop as it should be.

So since when was such slop submissions allowed?

Woosh?

Exactly, it is a joke of a post.

So why here?

It's parody.

Meta. Nice.

I thought the downvotes on this comment would be the funniest thing about the submission until the whole thing got flagged.

this is amazing

This is bad. 90% of the HN front page is just pure AI slop on any given day, might be time to start adding penalties for AI stories on HN ala NSA era.

It's satire, making fun of how Claude writes. That's the point.

Reply on news.ycombinator.com