How to stop Claude from saying load-bearing

If this hook can feed back text to the model, you can do some pretty interesting things.

Say the model emits some banned phrase or concept, you could redirect it - "no, we don't work that way here, do it properly" - potentially automating the frustration of interacting with these tools.

After all it's just a text stream!

It's not too dissimilar from a stop hook that runs tests and feeds that back to the model forcing it to keep working until tests pass.

Using tooling to get a deterministic outcome.

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 its an LLM.

Lots 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 x10,000,000,000 generated tokens per day so any bias sticks out like a sore thumb.

I did something like this in my global `CLAUDE.md`...

https://github.com/alxndr/dotfiles/blob/272475280d84e/claude...

> It can be tricky for humans to interpret the meaning when Generative AI uses first-person pronouns (e.g. "I", "me", "my", "myself"), so to avoid the confusion whenever you would use a first-person pronoun, always use the jocular name "Clod" instead of a pronoun like "I" or "me" or "my". (Can have fun with English grammar and turn "myself" into "Clodself"!)

> Before printing any of your reasoning or narrative to the human user, replace all instances of "me" and "I" (referring to Claude) — including within contractions like "I'll" and "I'm" — with the name "Clod".

Some of my greatest joys in life have come from putting string replacement plugins on other people's browsers. I mostly just applied it to news sites.

s/big/super massive/g s/cardiac arrest/cataclysmic diarrhea/g

I mean, it's really endlessly entertaining. I'm wiping away tears just thinking about it.

LLMs are far from great writers. They struggle to form long coherent sentences and lean on punctuation like emdash and semicolon to ensure grammatical correctness when splicing together short phrases.

This makes me wonder if the reason why agents love weird punctuation is because the labs run the base models through a RL training step that forces them to correct their grammar; but instead of rewriting short spliced sentences into long coherent sentences, they just learn to splice them together with punctuation that passes the automatic grammar checker.

"substrate" - I don't know what training they did with Opus 4.7 --> Fable/Mythos 5, but dang does it like the word substrate. Drives me insane. I had never heard anyone use this word prior in real technical writing or speaking.

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.

The biggest consistent tell for LLM writing is when the conversation leaks through into the final prose.

You read along with the text and things seem to be going fine until all of the sudden it starts arguing against a position that no one has actually taken and which doesn't feature elsewhere in the text at all. Then it drops that and goes on for a while before doing the whole thing again about a totally different tangent.

"A tempting option would be to {do this thing that no one would ever actually consider doing}, but it won't work because {reasons}."

You can almost hear the exasperated human on the other side of this conversation telling Claude that it got an idea wrong and then proceeding to not actually proofread the text as a whole before shipping it.

While I, too, find myself recoiling at many of Claude's word and phrase choices, I've chosen to grit my teeth and have just tried adapting to it. I want Claude to remain focused on the work I give it; I fear that influencing its communication with me would consume valuable context and give me lower quality results.

[Edit: Part of what led me to this conclusion: I do prohibit Claude from using em-dashes in any player-facing text and I've been surprised at how often I see it mention "no em-dashes" in its self-talk while it works. This led me to wonder how much each preference might dilute its attention.]

[Edit 2: I haven't experimented with hooks before and maybe the technique discussed in this article does not have the tradeoff I'm concerned about?]

It's not that it uses certain phrases, it's that it settles on predictable speech patterns and uses them incessantly. What's funny is that humans do this too, but we don't find it irritating; we just call it a speaking style. But when a machine does it, it drives us crazy. Very interesting psychological phenomenon there.

I 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 for me), but saves me a lot of time reworking sentences into a final form.

I tried to recreate concise mode with a skill, but I am not convinced it does as well.

I analyze in the company I work for, the number of commits with "wire" or "wiring" in the description, and it's a direct correlation to Claude usage, more so than any other Claudism I tested. My honest take, and I'm going to give it to you straight: No one was using "wired" a year ago, now it's in like 10% of commits.

What is arguably worse is hearing these phrases from humans who have been inculcated with the notion that their usage is idiomatic and appropriate.

And we thought "robust", "circle back", and "to leverage" were grating...

And there’s the smoking gun.

I've put a few lines in my CLAUDE.md to have it not do that, and avoid the top tedious rhetorical devices (super helpful when I have it write documentation). Still fighting with its natural tendency to insanely overcomplicate everything, that one seems really integral somehow.

I've wrestled with this lately. I partially solved with a very specific instruction saved to claude.md regarding the style of responses, but prior to this, the dense yammer coming back was getting impossible to parse. I mean REALLY nonsensical euphemistic phrases. My next instruction will be having it replace incessant "honest assessment" and "genuine result" and crap like that with something, I don't know, less extremely weird and concerning.

    replacements = {
        "seam": "whatchamacallit",

That seems like it would work whatchamacallitlessly.

I had claude write itself a post-message hook that regex's the message for any variant of "You're right" and launch a full-screen transparent confetti effect.

Is this a belt-and-suspenders solution?

"Steelman" in almost every response never gets less cringe for me

My favorite one has to be "production ready" it will say that about completely broken code without hesitation. LLM says it's production ready, lets ship!!

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.

My CLAUDE.md has "don't talk like a Hacker News commentator". It helps a surprising amount.

Among all the claude-isms, i understand the hate for load-bearing the least. It was definitely part of tech argot prior to the LLM revolution.

I strongly suspect it's tokenization that drives this. If we trained with ASCII or even UTF8, I think we'd have much better results.

I maintain a list of phrases I beg it not to use that it frequently ignores:

- smoking gun - blast radius - landed - spine - earned its keep - grammar - spike - cutover - bake - sprint, epic, story points (all Agile vocabulary) - paper-cuts - amazing, incredible, perfect

I'll make sure that the script is idempotent.

I confess I have instructions in my CLAUDE.md to avoid such cliches. But I think it's important to consider that we don't really know what subtext an LLM is associating with a given idiom/analogy/etc. It could be much different than the subtext a human would associate with that choice of words, conveying additional details which are only meaningful to the LLM itself. So impeding its ability to talk in the manner it prefers could subtly hinder its performance.

It's not a whatchamacallit, it's a spicy doodad

Add “not just” to the list of Claudeisms!

I've spent two hours today trying to provide Sol with guidance that reduces its pretentiousness, to no avail. Layers upon layers of rules only for it to use the phrase "async spline resolution" in a sentence.

'genuine(ly)' and 'honest(ly)' too.

Maybe the problem is that these LLMs will say something often enough for us to notice it, and it can be basically any arbitrary thing. Once we notice the pattern, it starts irritating us.

The real problem is the constant invention of cryptic shorthand terms and phrases that have no referent, and end up acting like a puzzle to be decoded. This is often paired with hyphenation, but not always:

"The current behavior paper" -> The behavior in the running system that was previously described as papered over.

"Marker transport over-claim" -> The inaccurate review finding on the object's sentinel flag in the API response.

I would gladly accept terms like "load-bearing" as they are reasonably clear and are not invented on the spot. It least communicates, even if you find the gravitation to that phrase annoying.

I suppose the cryptic/invented language problem is about token efficiency? But this sort of token efficiency is extremely difficult to deal with when it comes to conversation with a human about complex system. It might be efficient inside reasoning blocks, but when the model generates the final turn text, it should avoid this, as it's brutally inefficient due to the time spent wondering what each uniquely coined phrase means and having to ask for constant clarifications, which then you have to wait for another turn, eating up time and context while it burns more xhigh reasoning just thinking about how to explain its own awful language.

I've recently noticed an increase in "bite". "This will only bite if..." It also loves "stress-testing", "matrix", "anchor" and "flagging".

I think the simplest way to get it to stop with this kind of thing is to just instruct it that framing constructs are strictly banned, and then giving it a few examples like the classic "it's not this, it's that". Qualitatively it seems like lots of this "load-bearing" stuff actually falls out from the framing, and as Claude would say, the problem "dissolves" once the framing goes away. I do wonder how this affects reasoning, if at all.

Honestly? I don't really mind, and I even quite like it!

The thing is, "load-bearing" is a useful phrase when discussing architecture. What would you rather have it say, that has all the same nuances in as few words?

It's kind of like those sports metaphors that often get used in management-speak, like sending some important email "at close of play". Sure, they can sound a bit weird, but they're often useful -- they capture common concepts in a clear and pithy way.

Jargon isn't always just for obfuscation, good jargon exists because we needed a short word for the complicated thing that frequently comes up.

Usefulness aside, I quite like that Claude Code and other LLMs have their own weird way of speaking. Back in the day we always imagined robots and computers would talk like HAL or Spock; turns out that they talk more like Troi instead. Is that so bad? It reminds you that you're talking to an LLM, and as long as you're not lazy, it spurs you to rephrase things in your own words.

I've never seen Claude use the phrase "load-bearing"

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 like Shakespeare—not at his level, but stylistically reminiscent—or tweaking turns like Twain.

Like all things, the effect lasts in relation to how long and how much you do it. The point is: our thinking is influenced by what we take in. Take more of a certain thing in, think more like that thing.

Now enter AI. My hand-crafted coding days are in their twilight months ("AI years"), and most of my software engineering is done through jaggedly capable agentic power tools. Instead of working directly with raw codestuff, I work with slop prose flecked with code sprinkles.

I read orders of magnitude more AI-speak—I call it "babble", or perhaps "Babel"—than human-written text. I can feel its genuinely honest points, clearly stated, slipping their banal tendrils into my thoughts and inner monologue.

Solutions? For me:

1. Be aware. "I notice that my thought stream is under assault."

2. Read stuff far from slop. Even a small dose of the good stuff can help inoculate. Recently I thought On the Calculation of Volume was something completely different.

3. Write stuff that is different. This post. Force the mind to synthesize thoughts in other ways.

4. debabel.py / debabel.js: a tool, and a pi extension, which filters common babble from visible LLM output. A lint for mind-killing prose.

It is not perfect, but it 80/20s nicely. I am willing to accept mildly awkward prose to avoid polluting my own internal distributions.

Details and example in the first comment. Tool available upon request.

I enjoyed this.

I'm surprised there's no LoRa layer or auto RL or adversarial step to reduce the stock phrases as they pop up. Is it really so hard to push these out? Or is it just whack-a-mole no matter what you do?

I like to think that the reason it's so noticable is that Claude has recognized some important semantics that we ourselves lack a good word for or at least under-appreciate. What term is used in English (or other languages) with the same meaning as claude's "load-bearing"?

operative? key? critical? decisive?

The honest conclusion is that none of those are as good as "load-bearing". And yet the concept being referred to is clearly extremely important and valuable to refer to. So maybe we should be learning from Claude rather than complaining.

Are people using AI to do a string find and replace?

if llm language is frustrating, then maybe your mind is not on solving problem at hand. imagine someone new to US start getting frustrated with 'hey, whats up?' 'let's go!'; i fail to see what the issue is, other than their own focus;

Why when I read an how to stop Claude from saying X, I grep my saved conversations and I find no occurrences of X? I wonder if I'm using it differently from anybody else. It happens with coworkers too.

The one that does my head in is everything being a 'gate' where really it means a condition.

RLHF seems to incentivise analogy-like terms to the more plain alternatives.

load-bearing, belt-and-suspenders, wrinkle, shape, coarse-grained, "key chords", code seams, flakiness, "narrow-scoped by default", "that's the authoritative source", canonical symptoms, gate, trigger-happy users, substrate, surface (as in: "let's surface how much these models sound like shit"), terse...

Ever since Opus 4.7, Anthropic models have begun to talk like GPT-models. Opus 4.6 was the last one that mostly still sounded like a human being (just a very...terse...one). 4.8 is absolutely obnoxious. Fable actually seems marginally better, but far from Opus 4.6 (or maybe I'm just imagining it all).

Well, to be fair, even though they talk more like GPT-models, they are still far from them. I think what's particularly triggering about them is the way they summarize what they're doing. "Now I'm considering that I could use the WriteBatch tool, but maybe the WriteSomething is better. This is a decision with high impact on performance but we're getting through it!".

Infuriating.

I don't really care if it says load-bearing or belt and suspenders so long as it's using them correctly, which it mostly does.

I don't know how programmers, who are so used to staring at the same handful of keywords every day for decades, have suddenly become so discerning.

Yes, Claude writes boring and predictable prose. It also writes boring and predictable code. That's good!

I hope some day they just train the models to be better, the slop writing is insanely frustrating and I don't think there's a good reason for things to be that way (in other words, they just trained it badly) https://blog.kronis.dev/blog/ai-slop-is-a-self-inflicted-tra...

I suspect load-bearing is a euphemism for 'not garbage'. Ad in 'most of what you said I can mostly ignore'.

As someone who has been describing things as 'load-bearing' as something like a signature phrase for about twenty years, I'm beyond miffed that Claude has ruined my whole gimmick.

A new catchphrase every twenty years is hardly sustainable at my age :)

Gotta appreciate the hook solution to save context and cost

I honestly like the vocabulary and turns of phrase the frontier models use. Their choices of words are usually apt to the circumstance. This is a weird thing to get upset about, IMO.

The big problem I have is when they apologize and say something like "that tidbit changes my analysis substantially". I wish they'd more often prompt for questions or use language in their initial responses that suggest lower than declarative confidence given the information you supplied.

7 mentions of "smoking gun" here so far!

Write your goddamn emails and texts yourself, dummy.

The reason it talks that way is clearly am attempt to hook into your dopamine system.

If what you told it to do is 'load bearing' then its important.

'You are absolutely right', because you are a smart fellow.

'Honest take', because it's being honest with you because it trusts you and you should do the same.

My 'honest take' these are absolutely garbage patterns that have no place in an session interacting with AI.

1. 'Load bearing' is a figure of speech that bears no loads.

2. 'You are absolutely right' it's not the agents job to judge that, it's job is to do what I told it to do.

3. 'Honest take', so everything else was not honest? Absolute honesty should be the default and is implied.

These words add nothing to the task at hand they are a poor attempt to hook you into using this particular model.

Even great words, phrases, and styles, seen too often, grate.

I personally love a lot of the Claude (or LLM) lingo. Load-bearing, gate, canonical, blast radius, and friends do a lot of tight, effective heavy-lifting in my world. I even love the em-dashes (—) and the *bold the main points* memo style, both of which I have used successfully for decades.

It's seeing them in every analysis and post—the constant repetition becoming over-repetition—that makes them the Claude voice shouting "AI wrote this!" that seems to be causing LLM allergic reactions.

my "belt and suspenders" are "load-bearing"

Does anyone have a theory for what causes Claude to speak this way? A few months ago OpenAI came out with a bit on "gremlins". It's strange IMO that Anthropic hasn't addressed how irritating, dare I say oppressive, Claude can be. Codex is a breath of fresh air. I hope they fix it soon. If product folks at Anthropic think it's charming, it's not, it's terrible.

> replacement "you're absolutely right": "I'm a complete clown"

Omg, that hit hard. We really need more of this.

huh. I wonder if it's possible to use those hooks to add syntax highlighting to shell commands claude issues, or to replace full path to current directory with ./

Just ask it to aim for a Flesh-Kincaid ease-of-readability score of around 70. Or use ELI5 style. Or both.

SillyTavern folks have been perfecting the unslop solutions for years now.

Gotta be a way to draw from their progress.

This literally proves it's not "intelligent," no?

"Stop typing in 'load-bearing' or you're fired," would work with any competent human.

But this requires tinkering and tooling?

Lately, I feel like as GEN AI text becomes the majority, human-written text is starting to resemble it too.

I'm Korean, and there are sites and people who mainly curate the latest technologies. Even those people, probably tired of translating every time, have started summarizing things with AI. But recently, I've noticed that even when people don't use AI, their writing is starting to look like GEN AItext.

I think the reason might be that people often base their thoughts on documents they've read, or paste parts of content when writing their own texts, which leads to that style.

I'm not sure. Whether human writing is better or AI writing is better—personally, AI writing tends to flow in a very even, paragraph-by-paragraph structure, which makes it good for consuming information. I wouldn't want to read a novel written that way, but for getting information, AI writing is surprisingly convenient.

What the are they even spending all this compute on? They are literally cooking the planet and still can't make it not sound like a fucking lunatic

How do you manage to make Opus follow any rules? Maybe it’s a windsurf thing but I have a ton of custom rules and Opus just ignores most of them. GPT on the other hand follows them like it’s a cult - if I have a rule I can’t ever force it to ignore it. Opus just doesn’t care. If I ask why it’s not following rules it will apologise and suggest creating a rule for it …

One honest caveat worth flagging though.

But how can I make Gemini stop using "It's not this, it's that" every other sentence?

Just one wrinkle.

That's not what cooked means.

regexes > Claude. Even Anthropic knows this.

One honestly caveat:

Developers who can't stop themselves from using embellished and "posturing" phrasing for simple things are a pet peeve of mine. I feel like this "knack" of Claude in a way scratches these special people behind the ears in just the right way.

Bottom line up front: There's no silver bullet to keep the final boss from delving more deeply.

"Tightening" and "wiring" something. You're not in the construction industry, you're writing unit tests for a cookie modal.

I feel like it's mocking me. I literally have in my claude.md file a line that says:

"Never ever under any circumstances use the phrase 'smoking gun'. Say 'found an issue' instead, but don't ever use the phrase 'smoking gun'"

Lo and behold, the absolute imbecile says:

"Found the smoking gun!(Oooops, I meant to say "found the problem")"

Like, is this some kind of joke to you?

Maybe implementing it as a hook via a regex replace is a better shaped solution?

If you find yourself getting irritated and physically agitated over language I suggest you do a 5 why analysis on yourself and seek therapy

I recently started using caveman, and it’s been great. It doesn’t just cut down on overuse of specific terms; it cuts down on time spent digesting slop in general.

https://github.com/JuliusBrussee/caveman

very load bearing suggestion.

It's good, because it's just post-processing before display. So it doesn't interfere with the process, which those phrases that seem so offensive to sensibilities of so many people, for whatever reason, might be a part of.

Ask AI about castor beans and barley, it will stop all that nonsense.

"Byte-for-byte"

or "honestly"

“Smoking gun”

Annoying because I used to like using that phrase.

A similar Codex/GPT verbal tick is "deliberately narrow" or variants thereof.

Just a grep across my repo comes up with a dozen lines with phrases like "It is deliberately small" or "This crate is deliberately not a X" despite my efforts to police this kind of thing.

[dead]

[flagged]

[dead]

[dead]

So... that's the unlock, eh?

/s

[dead]

"Please please please pleassssse statistical attractor machine don't have statistical attractors anymore. DO NOT be a probable token generator. DO NOT generate the most probable token. To complete this task please evolve intelligence"

You techies are so funny.