site banner
PaperclipPerfector  1mo ago (text post)   2840 thread views

Friday Fun Thread for August 7, 2026

Be advised: this thread is not for serious in-depth discussion of weighty topics (we have a link for that), this thread is not for anything Culture War related. This thread is for Fun. You got jokes? Share 'em. You got silly questions? Ask 'em.

1
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

Write an erotic description of a young, skinny woman in a shopping mall.

You held back there, as one does with this subject...

The whole point is not to shrink back!

Now I think about it I'd be worse at writing smut than Deepseek V4 Pro. I could do a better plot and more lively prose generally, more creativity and wouldn't get confused... but it'd be so awkward I'd be unable to do it.

Also I think you'd be better off with longer prompts. I die a little when I see these benchmarks for creative writing with one sentence prompts. A good creative writing prompt is at least 600 words I think, maybe more than that. I'm not all the way into lorebooks but you gotta give the bot something to work with. If you don't have the LLM executing your ideas it will go full Generic Genericsson. Then again, maybe local LLMs are more constrained for context length.

I'm good at smut, but I also would feel a degree of embarrassment writing it at length. My last novel had plenty of gore, but I always had myself fading to black without being constrained by RoyalRoad's content restrictions. It's best saved for texting, where it gets me laid.

Now, I can't say if the bots have me beat, but I was wasting my time talking to LLMs, and challenged them to flirt with me (I was bored as hell, and this was part of a longer, more practical conversation where they were well equipped to know me).

GPT 5.5 High was ridiculously bad. I was laughing till I cried. Earnest cringe. The only way it's getting laid is pity sex.

5.6 Sol? Better, but that's a low margin to clear. I would not let it do my texting for me.

Fable, on the other hand? Alarmingly good. I was put off by the sheer idea of flirting with a chatbot, but it made me understand the appeal. I have too much dignity to ever resort to this, but Claude models are the equivalent of dudes in silk shirts, or women in slinky dresses.

Common local LLMs range from 128k to 1m context windows, and while I'd recommend aiming to use less than half of the window per session, that still covers most short stories easily. Very long prompts extend prefill time, but this only really starts to matter if you're running on CPU or mixed GPU+CPU, or have most of a book written already.

For metrics, Hecatomb's 85k word Wild Pair series (cw: furry, mostly m/f, extreme kinks in ways that mean decensored local LLM review is the only option) is 120k tokens, and takes about 30 seconds to calculate prefill on an nVidia 3090. For a non-smut example, Doctorow's I, Robot (cw: very annoying writing), is 15k words, 20k tokens, and was less than a second on prefill.

Conversely, LLMs will invent details, and while they'll be average, they aren't going to be that generic. This can definitely go weird places -- the tendency for LLM-driven names to end up as variants of Kael, Lyra, so on -- but even mild pressure will get you to specifics, for better or worse.

Yeah Kael syndrome is what I was thinking about.

But also are you gonna get any good quality after about 50,000 words in? Even in bigger models I notice writing starting to decline, errors becoming more prominent...

I'm not a huge fan of AI prose quality to start with, so for me the longer context is more helpful when reviewing or planning a work. Modern LLMs stay coherent longer into their context window, so it doesn't completely lose track if you prompt carefully, but it does definitely start falling back toward more sloppy results regardless of how carefully you're prompting it if you just try to one-and-done it.

I've been fooling around with agentic and programmatic approaches, and they work better in terms of output quality because you can do things like start new sessions with summarized old ones, or throw exemplar and style files near the extant context window, but the existing quality of tooling for that work is abominable, and it's still not good. Not sure whether that a limit of the tools, or a limit of my ability to use them.

I've recently been nooticing that something is definitely very weird with naming stuff in LLM-generated smut text. I'm usually a purveyor of uh, established can(n)ons so that usually helps corral the models into a more coherent mold, but recently I've been cautiously trying OC stuff based on old draftsand the naming "schemas" really stick out.

I don't know how to put it in proper words, but it feels like without a defined frame of reference ("you are {{char}} from {{vidya}}, &c"), there are certain "clustered" defaults that models resort to, based on which rough genre/setting the LLM mentally sorts your scenario into. My prompts are detailed enough that I don't get super generic stuff like my good ol friend Elara on a trek to the Whispering Woods shudder anymore, I'm not talking about those (though the existence of such certified hood classics independently encountered by so many people is in itself quite interesting), but the "mental models" the LLMs seem to keep are still quite noticeable in generic/open-ended OC scenarios - to the point that when bringing up say an as-yet-unnamed nearby town (with only the general setting and maybe name of the current one to go off of), the model's response will declare exactly the same %town_name% across several regens, despite being vaguely prompted and ostensibly taking a fresh crack at the worldbuilding every time. I have yet to test if those differ across LLMs, likely they do. Hopefully someone smarter than me is looking into it, or at least has nooticed.

though the existence of such certified hood classics independently encountered by so many people is in itself quite interesting

I had a look at what normal people put into LLMs as prompts, you should radically lower your estimates of consciousness, literacy and taste.

Don't think those can get lower at this point but sure, I'll count my blessings. Back when chub was still usable, I remember having seen a fork of one of my publicly posted cards, with only one difference - a very bobs-and-vagene-coded sentence added to its definitions and greeting message (from the user's point of view too, not the character's like the founding fathers intended!). Granted I have zero pretensions to poetic genius here, the card was like 600 tokens of simple descriptions, but the preferences and literacy of the average coomer have since become painfully clear. In that moment Rayon was enlightened.

I regret to remind you that 98% of people will never make a card or a fork or anything you can see on the user side... I'm talking about looking at it from the admin side, the shit people put in as prompts. AI is wasted on the masses.

You held back there

I did not. I truly have given this prompt to my decensored local LLM dozens of times, and the LLM's output always is much elaborate than anything that I would write. Could I in theory have made my output more elaborate? Possibly. But I don't have the competence to make those extra details actually sound erotic. (Inconsistencies in the darkness of the woman's skin? Waxing poetic about her thigh gap? A discursion on the shape of her nose? To me this sounds more excessive than erotic.) In contrast, the LLM, while going rather further than I intended to imply in the prompt (No brassiere? Lustful lip biting? Microskirt barely covering the buttocks? This is not a normal woman in a shopping mall.), is able to make added details actually sound erotic.

(And, again, I don't really care about gaining that competence—this is just idle dabbling.)

If you don't have the LLM executing your ideas it will go full Generic Genericsson.

I disagree there. It will always return a white woman if you don't specify otherwise, but it will give that white woman different outfits and make her do different things, even with a short prompt like this one.

I think that's what generic means though, it'll have that white woman in different outfits and doing different things but always described in the same kind of way and always the same kind of 'difference'. It's generic LLM smut, by the numbers stuff. I can't describe it precisely...

It doesn't surprise you like your one where it goes out of the way to be black. It won't surprise you much either if you give it a big prompt but at least it has somewhere to go that isn't totally generic if you set up the environment and dynamics in advance. They suck at coming up with good ideas unprompted. If you don't give it a foundation of your ideas it'll give you its ideas instead and it leans towards the median hard, unless you shove it out of median-land with a long prompt.

But they can write without shame, they have no trouble making it actually sound erotic whereas you and I would struggle.

LLMs don't give their full effort for a short prompt I think, only sometimes do they actually start to get into it (often deep in multi-turn) and there's a noticeable difference in how they write. Thus we talk about dry and wet Claude.

What is this place?

This website is a place for people who want to move past shady thinking and test their ideas in a court of people who don't all share the same biases. Our goal is to optimize for light, not heat; this is a group effort, and all commentators are asked to do their part.

The weekly Culture War threads host the most controversial topics and are the most visible aspect of The Motte. However, many other topics are appropriate here. We encourage people to post anything related to science, politics, or philosophy; if in doubt, post!

Check out The Vault for an archive of old quality posts. You are encouraged to crosspost these elsewhere.


Why are you called The Motte?

A motte is a stone keep on a raised earthwork common in early medieval fortifications. More pertinently, it's an element in a rhetorical move called a "Motte-and-Bailey", originally identified by philosopher Nicholas Shackel. It describes the tendency in discourse for people to move from a controversial but high value claim to a defensible but less exciting one upon any resistance to the former. He likens this to the medieval fortification, where a desirable land (the bailey) is abandoned when in danger for the more easily defended motte. In Shackel's words, "The Motte represents the defensible but undesired propositions to which one retreats when hard pressed."

On The Motte, always attempt to remain inside your defensible territory, even if you are not being pressed.


New post guidelines

If you're posting something that isn't related to the culture war, we encourage you to post a thread for it. A submission statement is highly appreciated, but isn't necessary for text posts or links to largely-text posts such as blogs or news articles; if we're unsure of the value of your post, we might remove it until you add a submission statement. A submission statement is required for non-text sources (videos, podcasts, images).

Culture war posts go in the culture war thread; all links must either include a submission statement or significant commentary. Bare links without those will be removed.

If in doubt, please post it!


Rules


Recommended Posts And Communities

Recommended Realtime Chats