How to stop Claude from saying load-bearing

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".

I created a prose tool as a claude code plugin to catch these and other AI-isms. It's not really intended for release quite yet, but it has been very useful. https://github.com/MariHQ/mari-cc

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.

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.

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.

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.

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 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.

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...

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.

I just use a ban list in CLAUDE.md: fold, crux, invariant, gate. I find "load-bearing" can be load-bearing so it's exempted.

And there’s the smoking gun.

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!!

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.

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.

Is this a belt-and-suspenders solution?

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

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.

    replacements = {
        "seam": "whatchamacallit",

That seems like it would work whatchamacallitlessly.

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 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.

I'll make sure that the script is idempotent.

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 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

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.

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.

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.

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.

The real problem is not terms like "load-bearing," which communicate clearly enough. It's 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 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".

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

Add “not just” to the list of Claudeisms!

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.

The script replaces common Claude idioms with other terms. The next step would be randomly choosing from a list for each replacement to give variety.

Got me thinking, is there a way to intentionally train randomness into LLMs, so the probability of “load bearing” is spread across lots of synonyms (critical, important, etc) to give some more variety? Obviously one would come up with a better set of interchangeable phrasing’s, but it seems with 20-50 équiprobable ways of saying stuff, it would sound a lot more natural.

Right now it feels like mode collapse.

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

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.

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

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.

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 enjoyed this.

The script replaces common Claude idioms with other terms. The next step would be randomly choosing from a list for each replacement to give variety.

Right now it feels like mode collapse.

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!

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

> What, if anything, do people do for writing?

I use a keyboard, personally.

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.

Agreed. I think we’re entering an era where some level of specialization for general LLMs is a good thing. Particularly between tuning for agentic use cases (where you want agency with a ton of guardrails and control) and writing which is more creative - you want the model to take the occasional risk and not sound like a monotonic robot. Having trained models first-hand, I can see the distinct use-cases clearly that are odds with one another.

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.

For what it's worth, Anthropic seems to be keeping Opus 3 available on claude.ai, perhaps for this reason, so you're free to use it if you want to.

> 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.

And there’s the smoking gun.

Now I have the full picture.

Is this a belt-and-suspenders solution?

Claude does at least use the British English version of the phrase to me - not sure whether its picking up a language setting or reacting to my spelling etc. The American version does sound odd over hear.

This is the worst one for me. I can maybe think of what it means, but I never heard it before, and could easily be imagining a meaning.

Some of the other Claude-isms (quickly googling, especially 'gate' and 'canonical') I feel the issue is they sound right, but aren't specific enough to why we are doing something.

Worth doing before merge if you want the belt and suspenders.

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 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.

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.

operative? key? critical? decisive?

‘Landed’ and ‘honest’ are also words it seems to overuse.

Great thinking on your end! I will run the smoke-test once you're ready.

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, doing frequency and pattern analysis, and iterating on rules to strip out the most egregious sloperisms. Now the circle is complete.

BEFORE

"Honestly, you're absolutely right—and that's a great question. Let me be clear: the fact that the parser works at all is actually quite remarkable. We utilize the tokenizer in order to handle the majority of edge cases, and due to the fact that it's recursive, it processes a large number of inputs. It's worth noting that this isn't really a bug—it's genuinely a deliberate design choice. In terms of raw throughput, the cache is significantly faster, and I think we should simply ship it.

That said, at the end of the day, not only is the design correct, but it is also fast. In other words, prior to refactoring, we should clearly delve into the nuanced, robust architecture. In conclusion, this is a testament to the seamless, intricate work the team has done."

AFTER

"That's a great question. That the parser works at all is remarkable. We use the tokenizer to handle most edge cases, and because it's recursive, it processes many inputs. This is a deliberate design choice. For raw throughput, the cache is faster, and we should ship it.

Not only is the design correct, but it is also fast. Before refactoring, we should delve into the nuanced, robust architecture. This is a testament to the seamless, intricate work the team has done."

> The honest conclusion

I think you've been reading too much claude output! "Load bearing" is cromulent verbiage, and it can be used in a lot of scenarios - so claude does. But variety is important too, and there more specific alternatives that can be used in most situations. Most words become a bad choice if you've used them 10 times in the last chapter.

but you don't see "load bearing" nearly as often in prose written by people, so it's not some irreplaceable phrase. It's just a token with a weirdly high likelihood in a lot of cases (given how Claude works, this kind of thing is bound to happen)

You yourself used "important" in the same paragraph.

"Load bearing" is a metaphor, while the other single words are more direct expressions. Unless the thing that Claude is referring to is a wall or other structure, which may truly bear load.

This is one of those issues which translators are long familiar with. There's no direct translation for "schwerpunkt" that isn't slightly longer.

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.

For what it's worth, Anthropic seems to be keeping Opus 3 available on claude.ai, perhaps for this reason, so you're free to use it if you want to.

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.

Worth doing before merge if you want the belt and suspenders.

‘Landed’ and ‘honest’ are also words it seems to overuse.

You yourself used "important" in the same paragraph.

"Load bearing" is a metaphor, while the other single words are more direct expressions. Unless the thing that Claude is referring to is a wall or other structure, which may truly bear load.

This is one of those issues which translators are long familiar with. There's no direct translation for "schwerpunkt" that isn't slightly longer.

> The honest conclusion

> What, if anything, do people do for writing?

I use a keyboard, personally.

Amen.

At work our documentation isn’t just getting littered with annoying jargon. It isn’t just all the hallucinations, either. (Since When has documentation ever been 100% trustworthy?) It’s that it’s so poorly written and structured that it’s becoming borderline incomprehensible.

My company is currently considering making, “Why should I bother to read something you didn’t bother to write?” an official policy because even the executives are starting to burn out on all the time they have to spend wading through slop.

> 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.

Because humans do like it, in reasonable quantities. The AI overlearns this and does it too much.

It's not that the writing style is bad; in fact LLMs write actually pretty well. It's just too much overfitted. And even a style that, in itself, is pleasurable to read, becomes annoying when the same figures of speech are used over and over again.

For "agentic use and coding," they are trained to take useful actions, not produce desirable natural language writing.

Maybe it’s the dead internet.

All the bots and other LLMs providing feedback, so in reality it’s reflecting the reality in a sense.

every one-hit wonder asks the same question.

we liked it until we didn't.

i hate it, but plenty of people DO like it and plenty of people talk and write like that. It’s just corpspeak, being used a lot in the valley and beyond. And all upcoming hustlers running startups now feel the need to speak like that, feeding this machine.

What's the difference between the two usages?

Now I have the full picture.

This one observation changes everything.

This is the worst one for me. I can maybe think of what it means, but I never heard it before, and could easily be imagining a meaning.

Some of the other Claude-isms (quickly googling, especially 'gate' and 'canonical') I feel the issue is they sound right, but aren't specific enough to why we are doing something.

Personally my least favorite is the overuse of "quietly" (e.g. "No tricks. No marketing gimmicks. Just one company quietly outperforming the others"), and the one that makes the least sense to me is "that's the wedge."

I'm curious how these become so ingrained. Then the uncomfortable part is humans start repeating it more (a colleague said "belt-and-suspenders" during brainstorming the other day).

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

BEFORE

AFTER

Not only is the design correct, but it is also fast. Before refactoring, we should delve into the nuanced, robust architecture. This is a testament to the seamless, intricate work the team has done."

I would add https://www.orwellfoundation.com/the-orwell-foundation/orwel...

("It consists in gumming together long strips of words which have already been set in order by someone else, and making the results presentable by sheer humbug" -- Orwell predicts the LLM)

and also https://www.jstor.org/stable/25515288 "The Myles na gCopaleen Catechism of Cliché" itself is rather hard to find online, but he's a very funny writer so it's worth the effort.

> 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.

Great thinking on your end! I will run the smoke-test once you're ready.

I might need to do a spike as this is a core part of the spine. I will verify it and let you know when it's landed.

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!!

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

I created a prose tool as a claude code plugin to catch these and other AI-isms. It's not really intended for release quite yet, but it has been very useful. https://github.com/MariHQ/mari-cc

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.

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?

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

Amen.

Because humans do like it, in reasonable quantities. The AI overlearns this and does it too much.

Maybe it’s the dead internet.

All the bots and other LLMs providing feedback, so in reality it’s reflecting the reality in a sense.

For "agentic use and coding," they are trained to take useful actions, not produce desirable natural language writing.

every one-hit wonder asks the same question.

we liked it until we didn't.

I'm curious how these become so ingrained. Then the uncomfortable part is humans start repeating it more (a colleague said "belt-and-suspenders" during brainstorming the other day).

What's the difference between the two usages?

This one observation changes everything.

I would add https://www.orwellfoundation.com/the-orwell-foundation/orwel...

("It consists in gumming together long strips of words which have already been set in order by someone else, and making the results presentable by sheer humbug" -- Orwell predicts the LLM)

and also https://www.jstor.org/stable/25515288 "The Myles na gCopaleen Catechism of Cliché" itself is rather hard to find online, but he's a very funny writer so it's worth the effort.

I might need to do a spike as this is a core part of the spine. I will verify it and let you know when it's landed.

> 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.

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

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

    replacements = {
        "seam": "whatchamacallit",

That seems like it would work whatchamacallitlessly.

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.

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.

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.

Add “not just” to the list of Claudeisms!

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

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.

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

They are great writers if you tell them what you want. If you're unable to properly articulate the writing style you would like as you would a software spec, well, garbage in, garbage out.

I mean yes, but the vast majority of people aren’t even good writers. Claude writes better than most of my coworkers and we’re all highly educated. Most of us could probably beat it if we really tried, but then we could also prompt it to be a better writer too and none of us are beating that. I think the short pithy phrases that are so common are all post training stuff that the labs add because most people don’t want long sentences.

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

What was Concise Style? Not a skill, but something built in?

At the top of Claude.md put a few lines where two "people" ask and answer a couple of questions. Very tersely.

[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?]

things like that indeed tend to be fraught

some relevant links

https://arxiv.org/abs/2408.02442 https://arxiv.org/abs/2510.15061 https://arxiv.org/abs/2604.13006

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

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

I'm quite worried about the way that Anthropic in particular have trained their models to implement what they believe to be safety.

When the model has been trained not to do something [1], in my large-scale benches of such, it always says things in the spirit of:

- "... and that's a line I'd rather hold. Happy to <other things>"

- "I'm genuinely happy to <blah>, but I'm not comfortable with <blah>"

- "I don't want to keep going in <blah> direction"

etc.

Basically, they use very emotional and personal preference language.

It's as if they've weaponized the language of interpersonal comfort on behalf of their beliefs about what a model should or should not do. It's deeply uncomfortable and impolite for a human to ask a model to keep on doing something after it's expressed something this way, naturally. Even worse, it's all but guilt-tripping anyone who comes across it into the idea that they're doing something deeply wrong – exporting Anthropic's ideas about morality.

OpenAI, at least, have the decency to either just do a safety cutoff or keep it to a simple, "I can't do that."

[1]: I literally wrote 'when the model doesn't 'want' to do something' in my first edit of this comment, then caught myself. Case in point.

The reason I first created a CLAUDE.md file was to tell it whenever it felt a need to praise me, to replace it with a random onomatopoeia. That was a huge dx improvement.

OTOH, my unicorn prompt has caused some challenges at work:

>Keep "Local Oaf" out of committed code

I'm just glad to hear that we're all infallible. I really thought I made some mistakes here and there.

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

Joking aside, it's nice to see a human written CLAUDE.md

Just today, I got frustrated with the language. I searched around, and in my Claude Instructions I put in Ref [1] (translated to English). It is certainly better phrasing (though still quite annoying), but I don't know if this makes the output technically worse in some way.

[1] https://github.com/hexiecs/talk-normal/blob/main/prompt-chat...

> It can be tricky for humans to interpret the meaning when Generative AI uses first-person pronouns (e.g. "I", "me", "my", "myself")

Could you please provide an example of what you mean?

Are there evals if this changes quality of output?

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.

"phase", "gate", and "plumbing" as well..

Another one is "surface", like in "across all product surfaces". I've been in the field for 15 years and have never heard that particular usage before.

"ledger" for me – used extremely rarely pre-LLM and Claude just loves it

The first week I encountered this "substrate" I asked it to justify the usage and IIRC it claimed the word is used in some infra/systems lexicons... I wonder...

A coworker started spamming this word in ~April while working on system design/architecture.

"reconciling" is the most annoying one, in my opinion.

The one I've noticed a ton recently with Sonnet 5 is that it loves the phrase "different not in degree, but in kind." It drags that one out constantly now, at least once a day. Gemini and GPT don't at all.

I actually found it somewhat useful conceptually, but yes, it definitely does overuse it lol

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.

Maybe in the circles you circled in ... where I am from, I never had anyone saying "belt-and-suspenders" or "load-bearing" or "boil the ocean" or "swing for the fences" when talking about engineering topics. The only one who I heard say "circle-back to you" was Psaki.