> (tap-select, drag-box, long-press deselect, two-finger scroll, pinch zoom)

This is another "AI-ism" I noticed, mostly in coding agents - they seem to be very fond of making up new "compound nouns" (and occasionally verbs) to sum up relatively complex and specific concepts into single noun phrases. I wasn't sure if it's to save tokens or if the AI uses this to get a concise "identifier" for a concept that it can refer back to later, but I found it very noticeable.

I find the resulting sentences hard to read, though it does get better if you're aware of that tendency and make a conscious effort to parse the noun phrases. But I guess since it's just intermediate output from coding agents and not text for essays or blog posts, it's fine.

▲ marginalia_nu 6 hours ago | parent | next [-]

Haha, I do that too sometimes.

It's a thing in some Germanic languages. Instinct is to merge nouns into word, e.g. 'lawnchair', but that gives you a red squiggly line, but 'lawn chair' also looks wrong, so 'lawn-chair' is the middle ground.

▲

ben_w 5 hours ago | parent [-]

First time I realised this was GCSE History lessons, looking at first world war posters like this one and going "huh, to-day with a hyphen…"

https://www.iwm.org.uk/collections/item/object/27774

▲

brador 4 hours ago | parent [-]

Badnami is Persian and literally means bad-name (like defamation of character).

English word origins are a fascinating rabbit hole.

	▲	ben_w 4 hours ago \| parent [-]
		> English word origins are a fascinating rabbit hole. My favourite example of which is Northern Ireland's Orange Order. The colour is orange, because that was the Royal colour of the family of the monarch it was named after, William of Orange, who was Dutch, titled after the principality of Orange which is named after the city of Orange which is French which got its name from the Celtic word for forehead or temple. The colour is named after the fruit, the fruit's name is a corruption "a norange" -> "an orange", which goes back to naranja which goes to Arabic which goes to Classical Persian which goes to Sanskrit. Meanwhile, the dutch word for the fruit is sinaasappel, Chinese apple, compare with the English word "mandarin" used for many different Chinese things.

▲ f3408fh 6 hours ago | parent | prev | next [-]

Yes! It's infuriating. I've tried prohibiting them in my AGENTS.md but it's not 100% effective.

--- AGENTS.md ---

## Plain words, not jargon

Don't use jargon-as-shorthand. Say what you actually mean.

- Don't say "load-bearing assumptions". Say "the assumptions the xyz depends on".

- Don't say "cross-service". Name both services, e.g. "whether the X service can derive duration without calling the Y service". "Cross-X" is confusing because it hides which things are involved.

- Don't deliver verdicts as abstract noun-phrases like "Cross-RCA double-counting is unfounded". Say it plainly: "I checked whether the same root cause gets counted twice across RCA runs, and it doesn't."

## No earth-shattering declarations

Don't hype findings. Skip "a critical finding changes everything", "now I have the full picture", "this changes the game", etc. Just state what you found plainly. Most findings are ordinary; report them that way.

## Don't reflexively hedge a "yes"

When the answer is yes, say yes. Don't soften every positive answer with a caveat: it erodes confidence in the "yes". Only add a caveat when there's a genuine, specific uncertainty worth flagging.

▲

godot 2 hours ago | parent | next [-]

Is "jargon-as-shorthand" not exactly that?

On another note, I find AI instructions like this (e.g. "Don't hype findings. Skip "a critical finding changes everything",...") more harm than good in my own uses. It changes behavior in subtle ways that makes it less predictable to me. I'd rather it has its own AI-isms and quirks, that I've fully gotten used to, and I know what to expect. I know when it says certain things, in certain ways, that's what I think it means. Quirks and AI-isms don't annoy me, I get used to how it states things.

▲

f3408fh 2 hours ago | parent [-]

Lol! Good point. I did use Claude to write the rule, and it ironically wrote the exact thing I asked it to avoid. I agree that it might be best to use the model as-is, to get the intended experience.

	▲	gitaarik 2 hours ago \| parent [-]
		Also I find it interesting to learn the jargon. It basically compacts information in fewer words, although more complex words. But when you are familiar with the jargon, you can unpack the sentences in your mind. And like that, you need less text to read and write prompts. So less reading, writing, and tokens!

▲

skerit 6 hours ago | parent | prev | next [-]

I thought it was just Opus 4.7 and 4.8 that did this. Do other models do this too?

Anyway: in my case Opus absolutely did not follow a similar instruction in the CLAUDE.md file. (But then again: it hardly followed _any_ CLAUDE.md instruction properly)

	▲	embedding-shape 6 hours ago \| parent \| next [-]
		It's stupid, but have you tried telling it to follow it? "Make sure to follow the guidelines from AGENTS/CLAUDE.md" etc, seems to (sadly) make some difference in most harnesses and models.
	▲	mikeryan 6 hours ago \| parent \| prev \| next [-]
		In all my CLAUDE.md and AGENTS.md files I have a line to fix pre-existing issues. I don’t know what it is but every agent I’ve tried through Claude code (including deepseek and GLM) will actively try to avoid fixing pre-existing issues. I even added hooks to Claude and git to try to get them fixed. If I leave a bailout for myself agents will find it sit and ask if it can push with no-verify or an environment variable in the case of Claude hooks instead of trying to fix an issue it didn’t cause.
	▲	futuraperdita 5 hours ago \| parent \| prev [-]
		For me, Opus 4.8's thinking traces for the chatbot will sometimes willingly ignore instructions, saying something along the lines of "I've noticed an instruction in the system instructions that states I shouldn't do this, but if I don't do this, I'll not provide the answer the user is looking for. I will ignore that instruction."

▲

xg15 6 hours ago | parent | prev | next [-]

Yeah, I wonder if part of the reasoning is built around those phrases, and therefore it can't get rid of them easily.

> "now I have the full picture"

I always interpreted that phrase as a sort of marker to delimit the phase in which it explores the codebase and gathers information from the phase in which it implements the changes.

Not sure if it's still done, but I think some months ago there was discussion that some of the phrases are injected by the inference loop to "steer" the model - e.g. "But wait" if a thought block was too short etc. Obviously such phrases couldn't be influenced by the prompt.

▲

Sinidir 2 hours ago | parent [-]

Yes these things happen as part of RL Training. Same way that you can see the "But wait ..." phrases in thinking traces. They get rewarded.

	▲	f3408fh 2 hours ago \| parent [-]
		Out of curiosity, how does something like "But wait..." get rewarded?

▲

spudlyo 4 hours ago | parent | prev | next [-]

NO DEFORMED FINGERS!!!

▲

wonnage 4 hours ago | parent | prev | next [-]

It’s crazy that straightforward rules like this can’t be followed and yet they think they can gate Fable

	▲	arcanemachiner 4 hours ago \| parent [-]
		That rule can be followed, but it gets a little tricky when mixed up with the other ten thousand rules that it's following at any given time.

▲

lostlogin 6 hours ago | parent | prev [-]

> Yes! It's infuriating.

No, it’s good. When they stop doing this, it’ll be harder spot the machine slop.

▲ trentor 6 hours ago | parent | prev | next [-]

Maybe LLMs are just Germans.

▲

Rexxar 6 hours ago | parent | next [-]

That's the G in AGI.

	▲	sscaryterry 6 hours ago \| parent [-]
		Artificial German Ingenieurwerk

▲

lacy_tinpot 6 hours ago | parent | prev [-]

This isn't good news...

▲ shibel 5 hours ago | parent | prev | next [-]

I’m (sorry for the lack of humbleness) a very fluent non-native speaker and writer, and this is by far my biggest challenge with Claude. It stitches together 2-4 advanced concepts into one or two words and I always have to ask it to “unpack”.

I don’t think it’s easy on native speakers when it happens, but it’s even harder when you’re not.

	▲	gregoryl 4 hours ago \| parent [-]
		Its hard for native speakers. Information density makes for rough reading.

▲ jorl17 6 hours ago | parent | prev | next [-]

Excessive-hyphenization is ai-hyperfixation

▲ topgrain2 6 hours ago | parent | prev | next [-]

That’s… about how I might have written that.

▲ mikeryan 6 hours ago | parent | prev | next [-]

That and finishing a statement with an em dash — that’s what AI does.

▲ rossant 5 hours ago | parent | prev | next [-]

That, and also the very long comma-separated lists with sometimes 10+ items.

▲ daveguy 6 hours ago | parent | prev [-]

FYI, AI isn't fond of a goddamn thing. They have token prediction quirks that don't follow typical English.

▲ ben_w 5 hours ago | parent | next [-]

Few ever cared. Find one non-pedant who would object to the personification that follows:

  "The evening settled over the city, drawing the light out of the streets one corner at a time. Windows blinked awake with lamplight, and the wind moved through the alleys restlessly, leaves brushing against walls before gathering themselves along the pavement. In the distance, the river kept its steady argument with the stone embankments. When the night pressed in, the weather became increasingly angry, until it was a raging storm."

In the affective sense, evenings don't settle, and street lights are not drawn out, windows don't blink, and wind isn't restless. Weather can neither be angry, nor rage.

But such personification is a natural part of how the English speak.

	▲	folkrav 3 hours ago \| parent [-]
		Personification =/= anthropomorphization

▲ sawjet 5 hours ago | parent | prev [-]

Personification is a figure of speech. What you say is technically correct but we don't need to declare this every time humans discuss how LLMs work.