343 comments

[ 3.0 ms ] story [ 116 ms ] thread
And there’s the smoking gun.
And the footgun (although I haven't seen a smoking footgun yet).
[delayed]
That's a real distinction, you're right to point it out.
You're right, and that's the sharpest thing you've said all day.
Nuance quietly surfaced.
You're right to push back on this. The honest take is it's not a smoking gun -- that's a sharp critique.
You're right to pushback, and that's on me.
I'll make sure that the script is idempotent.
That's not really a claude-ism. Its an important requirement for a many asynchronous tasks.
I dunno. Claude recently burned a lot of tokens trying to test an expensive task for idempotency.

While the task I was working on should incidentally be idempotent, it wasn't that critical. I never asked, or even suggested, idempotency. Yet it insisted on testing it was.

I need to scrutinize the plans. Or just not use Claude and use pi instead.

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.

Is this a belt-and-suspenders solution?
Worth doing before merge if you want the belt and suspenders.
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).

I heard "belt and suspenders" at least 20 years ago (meaning multiple solutions to a problem with backup in case one fails), and maybe would be longer if I were older. You could blame Claude for overusing it or importing it to other cultures maybe, but it's not in the category of invented phrases or ones that only barely mean something in the specific context Claude used them.
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.
Yes, and that actually sharpens my previous conclusions.
That's an importance nuance and makes the previous statements even more clear. I have the full picture now.
Maybe implementing it as a hook via a regex replace is a better shaped solution?
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.

> Nowadays, with the focus on agentic use and coding, it seems models have all been RLHF’d to death

This has also lead to unrelated associations by which some people went from seeing better coding capabilities and extrapolate to assuming better thinking overall. One only has to watch youtube videos of AI "normies" trying to use LLMs the intended way to see that the improvements on coding doesn't translate to other applications. Basically from AGI "goals" they are now hyperfocused on coding agents, until the next marketing breakthrough rears its head.

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

Gotta be a way to draw from their progress.

There are no real solutions, it has to be fixed during the training. There are two workarounds that ST folks generally do:

- Samplers that increase prose variance. They require running the model locally, dumb it down, and never fix the actual issue, which is mode collapse leading to semantic collapse and rigid mapping of input to output concepts. The model still expresses the same ideas.

- Let the model write anything if it couldn't resist, but check and fix it in the verification pass. This solves the semantic problem, but cannot solve the variance since the second pass is also subject to rigid mapping. The verification prompt can be randomized to a degree using pretty clever schemes, but of course this also fails in predictable ways.

Just ask it to aim for a Flesh-Kincaid ease-of-readability score of around 70. Or use ELI5 style. Or both.
Flesh Kincaid sounds like an excellent name for a Scottish porn star. I'd never heard of this, turns out it's Flesch, but thanks for the TIL!
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

I love it. It also saves you tokens and it has been linked with more accuracy.
The token saving is oversold, from what I can tell so far. These days output tokens are just the tip of the iceberg.

If anything the real value is it saves my brain from going into power saving mode by lunchtime because I haven’t spent the day reading pages of output when a sentence or two would do.

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

“Smoking gun”
I want to be straight with you, I overstepped by naming it a "smoking gun."
"Honest assessment: I was wrong to say I was being straight with you. You pointed out that a "smoking gun" is a sign of evidence, and I clearly didn't have any. This is not a bug but a gap that can be fixed like [this]. Give me the word and I'll wire it in."

··You've hit your monthly spend limit · raise it at claude.ai/settings/usage

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.
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

More: rider, "x, not y", "is real", "prove" (in situations which only admit empirical evidence), nailed down, payoff, decisive, reassuring

just generally a nauseating amount of embellishing, (also self-)congratulatory language, superfluous self-judgment, and jargon, as well as sus constructions along the lines of "i could have lied to you but didn't", all of which appear to be impossible to have it avoid in the long run

You're absolutely right to flag these. We could enhance the authors method by using hooks and claude.md as a belt-and-suspenders approach— with hooks behaving as a robust load-bearing idempotent production-ready sidecar. The comments here provide the smoking gun that sharpen my previous conclusions about Claude's vernacular. I'll get started on a quick smoke-test of this system and let you know when it's landed.

Want me to take a first pass looking at the blast-radius this vocabulary change could effect?

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.

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.

(comment deleted)
> The honest conclusion

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

You don't think me using "honest" there might have been a tiny bit of (on-topic, and therefore appropriate) trolling?
You're serious?

Operative, key, and critical are all more correct to me in this context.

For me, "key", and "critical" merely say it's "important", but don't convey the sense that "out of the mess of connected concepts we're discussing, the one that is actually interacting with the thing we care about, or at least dominating the interactions with the thing we care about, is X".

"operative" is a bit better, but I think of it as referring to grammatical interactions, i.e. interactions at the level of language mechanics rather than semantics.

In the figurative sense it's highly versatile across contexts, but still replaceable. For example:

"Her optimism was load-bearing,"

versus:

"Her optimism was enduring."

Exactly the same meaning and connotation. It stands to reason that the terms with the most semantic flexibility will have preference across all contexts. So in response to:

> maybe we should be learning from Claude rather than complaining.

I'd say let's not steer ourselves into regular language and keep some vivacity in our expressions.

> Exactly the same meaning and connotation.

No, it does not have the exact same meaning.

The first means that her optimism kept her in some functional state, without it, she would collapse.

The second means that her optimism continues over time, despite obstacles.

> Claude has recognized some important semantics that we ourselves lack a good word for or at least under-appreciate.

Ah, I love when Claude reads our collective minds and fills in the gaps to address the load-bearing seams genuinely with an honest caveat.

I mean we have all kinds of under synonym'ed words. Just look at how few we have for "smell" (as in the act of smelling), and then how overloaded the word smell even is.
'Load-bearing' is a physical analogy. Other words like 'pillar' imply the same physical analogy.
> the concept being referred to is clearly extremely important and valuable to refer to

On the contrary, stock words pop up more easily when it has less confidence.

Stock phrases are a correctness smell.

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'd contend that Claude's prose is not boring. It's generally overly grandiose waffle with a cliche or two punctuating every other sentence. It's good for tasteless marketing copy, sure. It's inappropriate in most scenarios.
> which it mostly does

I don't think that's true. I find that it way, way over-intensifies: eg using "load-bearing" for something that's just "kind of necessary although we probably could find a way without it". My personal gripe is how easily it uses "incredibly" or "wildly": just today it was telling me that something is "incredibly cheap" to mean that it's not over-priced ("cheap" would have been okay and even then, barely)

I definitely care. They are impressionistic responses that smooth over exceptions and lack precision and are often completely wrong in the sense that, when pressed, the agent will acknowledge the lack of rigor in the response. "That phrase was wrong of me to use. There is clearly an exception to what I just said, and it goes like this..."
I hate it because put together, it all increases the cognitive load of understanding what it's saying. It routinely invents phrases, and every single one makes me pause and think "okay, what the fuck does that mean". Half the time the phrases are incoherrent.
> replacement "you're absolutely right": "I'm a complete clown"

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

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.

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.

This is why when I even sniff a hint of Claude phrasing I close the article and block the person on all devices. I'd literally rather be lobotomized than sound like this shit. The fact that anyone can read AI text without immediately starting to dry heave is a pretty damning indictment of their character
I actually think it's better. Back when access to knowledge was only available in English, there was a lot of mistranslated information in my language (Korean) that was worse than AI slop. These days, the translations are done by AI, so the tone may be awkward, but the content is more accurate than before, so I don't mind.

So that's the difference. I'm already living in a degraded environment, so this actually feels like an improvement to me. But you, coming from a better environment, perceive it as worse. It always seems to depend on cultural context.

[dead]
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.

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.

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.
We don't have to live with this. Increasing the temperature (randomness) would fix it.
Fascinatingly, I'm now so allergic to certain LLM-phrases that I immediately noticed your use of Not X but Y in this comment. Maybe that was intentional, maybe not, but it's a funny illustration of how odd this language rabbit hole has been!
It was not intentional, and that's what makes this thing so weird. I wouldn't categorize my sentence that way because it's subtly different enough than the LLM version, which has a very punchy cadence.
Sounds good, thanks for your response. I didn't mean to denigrate your word choice at all, it's mostly that I'm hypersensitive to that kind of phrasing now because there's so much auto-written stuff on e.g. Substack, LinkedIn, etc. Sam Kriss has a nice article about it all.
Are you using the tools a lot and having first-hand exposure that gives you this sensitivity to phrasing? Or are you reacting to second-hand exposure? To a large degree, I've been isolating myself from the LLM craze. I have zero natural interest or impulse to prompt an LLM and read the results. Almost all my exposure is second-hand and involuntary. So, I haven't trained myself to know what phrasings are typical of which LLM product.

I don't feel as triggered LLM phrasing as people report here. At most, it feels like the same inane corporate jargon I've rolled my eyes at for my whole career. Perhaps it is amped up a bit, with too many forms of jargon multiplexed? It's a bit like when multilingual people code-switch too rapidly or even start to form some pidgin language. However, it is lacking the shared social context for this switching to be communicative. It's a bit more like spinning the dial on an old radio with random cuts between programming styles.

Stripped bare, I think What bugs me is the aggravated feeling that I am wading through word salad, and no longer being able to give the purveyor the benefit of the doubt. It was frustrating enough in the past, when it came from someone who was struggling to write or express themselves well. But now, it carries the implicit insult that they didn't even try, and it is constant and unrelenting.

So for me it's not the phrasing, it's that the phrases eventually don't add up. The meandering feels like a random walk. I get the same feeling from a lot of the egregious generated code I see in my day job. It's all superficial window dressing, but seems to miss the signature of an actual mind grappling with ideas and having intent to communicate.

It feels like we're trapped in some elaborate conceptual art piece, confronted by impenetrable symbolism. It invites nihilism but doesn't seem to actually reflect an artistic intent. The abyss gazes back...

If it uses a specific style for each user then this would still be fine. Problem is it does the same style for everyone. We need personality
If training models ever becomes 'cheap' for whatever definition of cheap you want to use, I suspect that will happen. With the current costs of a GDP of a small nation I don't see this likely for the time being.
It drives us crazy because everyone is using the same 2-3 different machines. So rather than each person having their own unique speaking style, the whole world (or, everyone that publishes direct LLM output) is now speaking in the same couple of styles.

And these machines all tend to converge on very similar styles; they have huge amounts of overlap in training data (much of it being already obnoxious internet marketing), they frequently train on each others outputs, and the RLHF process has a tendency to emphasize certain kinds of "cheap win" styles of speech.

it’s not a psychological phenomenon. If a human engineer constantly used pompous language to deliver unvetted information (the number of claude slop root-cause analyses i’ve read where “the smoking gun” is a red herring) we’d rightly consider them a moron
"Here's why this version is bulletproof" right before it fails in exactly the same way as the previous bulletproof implementation...
I didn't articulate it, but what I meant was that I think we could swap these expressions out for _anything_, and we'd still find them irritating.
People do swap out their expressions all the time. There are influences everywhere that we absorb.

That doesn't matter. The underlying ideas are more important than the words. That's what people are frustrated with. I don't understand why this has to be reiterated for years on end, but LLMs are not intelligent. They just model language.

Who is we? Own your insults and the consequences of them sir.

When prompting an autoregressive token generator entity to do reasoning on a word logic puzzle you may find value in preferring it to produce rigorous predicate logic step notation with explicit delineation of its generated claims/hypotheses on where to look before wasting 30 dollars on a "debug this" prompt.

The industry will probably will probably coalesce around including the chat history in git MRs to reduce this shenanigans.

Humans are capable of introspection, so, if you develop a verbal tic, you might eventually notice and say to yourself "I've used the word 'load-bearing' (or whatever) a bit too often lately, maybe I should try to cut down on it?". LLMs are not...
...or we call it an overused catch-phrase.
> What's funny is that humans do this too, but we don't find it irritating

I make fun of people all the time for shoehorning their favorite phrase into every context where it doesn't apply.

Wow sounds like you're streets ahead.
> 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.

When a human does it, it's identifying. Like the timbre and dynamics of their spoken voice itself, It distinguishes them from the dozen other people you're working with on the project and the thousands of people you encounter through your days. It's signal

But when we have a handful of popular models, and they answer every question everybody has, and get quoted and forwarded everywhere, and are used to reformat and rephrase personal communication... that signal becomes noise.

Rather than voices disinguishing sources in the cacophony of our lives, everything and everyone starts to sound the same, and we lose key information that we're biologically and culturally accustomed to relying on.

Some people are likely unbothered by this in the way that some people are face blind or colorblind, and so don't see the problem. But as we see in discussions like this, many many people do get bothered by it, even if they don't yet have the insight as to put their finger on why.

You could say it works perfectly well, it is identifying indeed. Of Claude and of people who use Claude's raw output instead of expressing themselves.
> but we don't find it irritating

Yes we do! My wife keeps saying "100%" and after I pointed it out she's stopped.

Also I talk to dozens of different people in my life and they all have different overused phrases. Much less tedious when there's variety.

Finally most human don't do it nearly as often as AI, and they're not quite as LinkedIn as AI.

We don't find it more annoying because it's a machine - it's simply more annoying.

I went through a “100%” phase recently and couldn’t for the life of me understand why I was suddenly saying it ALL THE TIME. Brains are so weird.
Did you negotiate her down to "99%"?
It's like a new fad word. Gnarly, cool, bogus, rizz. When a few people use them it's new and interesting. When all of culture catches up and overuses them it's annoying as your gen-Z saying 6/7 40 times in a row.

The problem with millions of people using a few model is it's not 40 times in a row, it's 40 million!

Introduce "hundo p" and "hundy" to her
If LLMs were humans I would find that human absolutely insufferable. It is very much about the language.
We do find it irritating at times. Office jargon, corporate buzzwords, etc. Claude communicates like the worst, most irritating project manager I’ve ever worked with, obscuring the most straightforward conclusion with layers upon layers of stuff so that its point is almost lost. I’ve largely gotten it to avoid that behavior with me, but bits of it sneak through. It couldn’t talk about “scaffolding” for a few weeks before I hammered it into submission.
During college, my gf at the time learned the word "plethora" while writing a paper. There after it was like she tried sticking it into any conversation where "many choices" or "a lot of options" would normally go. It annoyed the crap out of me.
I find it irritating with humans. "last but not the least" always distracts me as I then consider maybe the last item _is_ the least. & what is with everyone saying they want to "double click" into meeting items
I'm guilty of this too, but at least my speech tics are mostly a unique blend to me, and they also tend to change seasonally. Meanwhile the emdashpocalypse has been going on for years.
> humans do this too

Here, look at this amazing pathfinding algorithm you should use. It takes you to the wrong place 30% of the time but humans do it too so that's ok.

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.