>>540544434
Sneedy thread

I wonder why they chose NAI GLM, but I'm glad they're moving up from Erato.

What's new in the hood my niggas?

>>540544671
I'm curious if they did try making a homebrew MoE, and it didn't go well and they ended up settling on one of the chink ones instead

for me, it's writing like a girl so I can pull the good vectors

>>540544671
GLM-4.5 is the best open weights model I've tried (for RP) so I'm not surprised they picked it. Well, I'm surprised they actually had good enough taste to pick it instead of doing something retarded. It's genuinely a really good model and probably? the least censored/restrained.

>>540545754
What about claude opus 4.1?

>>540545754
>the least censored/restrained
Nah that's still DeepSeek 0324
It's a good choice though

>>540545910
I do not really care for ozone. Regardless, I am positive their fine-tune will make it punch above its weight, especially given the base model does not so far have any noticeable quirks like Erato did.

>>540546060
How can I try it for free?

>>540544671
Simple. Deepseek and Kimi is too big.
Why do you think people don't use GLM before?
Previously, even non-NAI users here only talk about Deepseek/Kimi/etc. But look, we now somehow have multiple GLM users come here to praise it.

>>540546193
When they release it, they will likely renew their trial for all accounts with a current or former sub.

>been using deepseek 3.1 on OR completely for free
>current prompt is 19k tokens of lorebook like info
Is there any point in returning to NAI if I don't need imagegen right now?

>>540546060
...isn't this the instruct model?

>>540546269
Mostly because I still prefer DeepSeek / Kimi
Maybe their finetune will finally draw me to GLM, but we'll have to see

>>540546386
I think he meant the base they're finetuning
But yeah, it's the instruct model

>>540545484
They saw the writing on the wall that in an age where triple beak models are the minimum needed for competitive model performance, their Coreweave-rented Shoggoth cluster (few hundred H100s plus whatever other GPUs they had from before) cannot possibly train anywhere quick enough. Especially while simulatenously doing inference too.

Homebrew models are dead, and that's okay. Chinks put out decent stuff.

>>540546625
From idle tests with the model as is, it appears better than DeepSeek and Kimi for my purposes, if nothing else. Terminus kind of dropped the ball, but I have enjoyed Kimi. That I have a current sub means I no longer have to waste my tokens rerolling with Kimi.
I still think the real pudding will arrive whenever they drop their fine-tune.

>>540546386
Can you stop noticing things? If NAI uses it, it must be good.

>>540546386
>>540546947
Since when are instruct models bad?

File: 1645585439315.jpg (711 KB, 1103x1087)

711 KB JPG

hand over your improved system prompt now

>>540547414
Since the first one that wasn't NAI, until now.

>>540548060
That has never been the case here.

so what happened, is NAI running out of funds and turk snapped out of his lowtaxian stupor?

>>540548215
https://arch.b4k.dev/vg/search/text/instructshit/
https://desuarchive.org/g/search/text/instructshit/
https://arch.b4k.dev/vg/thread/459191694/#459264624
>The only real reason NAI is still in the game is because literally nobody else finetunes models on prose and literature for the purposes of storytelling. It's all endless chat/instructshit tune of the week #435234. Honestly a little surprising how little interest there is in it.
According to the last post, this thread basically considers NovelAI to be dead.

>>540548521
That means you can fuck off and kill yourself. Finally, the good ending.

>>540548445
>lowtaxian
ah, vintage

>>540548521
>only forty-five and eleven results
How does this proof anything? Especially when many of the comments those posts receive are people arguing against whoever posted those. You can't just assert comments by randos are the sentiment of the thread...
Anyone can shitpost. Do you have any actual proof that people here hated instruct?

>>540548445
seems that way

>>540547719
Now we have to add 'convince a robot to stop doing stupid shit' to our setup?

>>540547719
When I get home from work, sheesh
I haven't even cracked this bitch open yet

I haven't used NAI in what feels like decades because turk obviously gave up on it because imagegen. It feels me with a certain kind of amusement that all the smugposters are not confronted with the dude implementing an off-the-shelf instruct model. Just cancel the sub and sub to something like nanogpt man. It's cheaper, too.

>>540549413
I will never give Altman my money.

>>540548719
"Instructshit" is the difference between this thread and /aicg/. You don't need two generals to talk about the same type of model.

>>540549754
Ah, the hand revealed, and it's... really? Just the same dumb merge shit again? Kill yourself if that's all you have the energy for nowadays.

>>540549754
I fail to understand what problem you have with /aids/ existing, but if you don't care for the community, why don't you leave? Nobody is making you stick around in a thread you think doesn't deserve to exist.

File: 1614976714123.jpg (39 KB, 472x472)

39 KB JPG

STOP FIGHTING ALREADY
I KEEP GETTING EXCITED ABOUT SOME FUN NEW POST AND THEN IT'S JUST YOU PEOPLE

>>540549997
Okay, since you asked nicely I'll stop engaging.

>>540549601
nanogpt has nothing to do with altman, it's a provider that basically gives a sub to current open source LLM models like glm, deepseek and kimi, for $8 a month. It also offers imagegen but I'm not sure which models. I know it does offer Chroma. They also provide on-demand to other models but the subscription option is extra (and a little hidden on their site)

>>540550115
>Pay-Per-Prompt AI Service
I have no interest in this.

>>540550274
only their other models are pay per prompt, GLM, kimi, deepseek (and I think a few others) are unlimited.

>>540550274
https://nano-gpt.com/subscription

>>540550532
How many times must I tell you I have no interest in this random service you're shilling before you quit responding to me? OpenRouter is better than this shit.

>>540549965
A thread with no identity doesn't deserve to exist. That's what happens when the last thing that differentiates this thread from the others disappears. GLM 4.5 can already be talked in /lmg/, /g/aicg, /vg/aicg, /chag/, /vpcai/, /wAIfu/, /2huAI/... What does /aids/ add? NovelAI's special prompt? You can mark today as the day /aids/ died.

>>540551368
See you in December or February, when their fine-tune arrives, and I bet you this thread still won't be dead. Despite your desperation to kill it, lol.

>>540551368
Kill yourself.

>>540551368
considering that we were here long before the other AI threads, they should've all just come here instead :)

>>540548676
/aids/ is the SA of AI threads.

>>540551735
There's a good 10 bux joke there.

>>540551735
I guess we are a bunch of goons

>>540551368
...he said for the thousandth time

>>540551735
dear turk,

>>540553968
PINGAS

https://rentry.org/2hwnkkvd

>>540554573
model? creative writing? What

the service

File: file.png (4 KB, 235x56)

4 KB PNG

They have been cooking the tools (not the model) for a long time.

>>540554573
we're all so jaded by what we got now but if you think about it, it's amazing that a computer wrote this

I wonder if Ephemeral Context would be useful for this model.

>>540555658
>instruct model
>"please write in different style thx!"
Based! The most basedest $25/month I have ever paid!

>>540555925
Yes, it is based.

Anyway, I was more talking about how that feature was teased back when Erato released. Which gives people a time-frame for how long they have been working on things. In other words, no, they weren't sitting on their asses and twiddling their thumbs, as certain people here deluded themselves into believing.

>>540555925
I can finally stop paying that Russian guy to suck me off and switch completely to textgen.

File: 1733593785613601.gif (513 KB, 500x281)

513 KB GIF

I thought this day may never come.

>>540554573
i too like to write letters to LLMs but they are usually not like this. What model is this, what prompt did you use?

>>540556318
More like cum.

>>540554921
>>540556359
deepseek, I'm experimenting with multiprompting. I have a hard time pushing the model to go past 2000 words in a letter without kinda devolving. It seems to be the limit for deepseek for one reply in that format, no matter what I do.

>>540556210
>select text
>paste it to a blank story
>tell the model to rewrite it
>copy the result
>replace the selected text with the result
A CS undergraduate can code this in an afternoon.

>>540556943
What's the name of your service? Surely you created and financed one... Right? Unless you're not a CS undergraduate...

>>540556894
>deepseek
>>>/aigs/
This thread uses GLM.

>>540557171
This thread isn't exclusive to any particular service or model. Why do you pretend otherwise?

How does it compare to Dragon? Or Calliope?

>>540551368
Are those all the tabs you have open, Ctrl+Fing for any mention of NAI?
Kek, you fucking loser

File: 1640182065126.gif (1.83 MB, 288x377)

1.83 MB GIF

Now for the grueling task of transferring all the prompts and lore I've been working on the last 6 months from Sillytavern to NovelAI. I will not miss it. I hope GLM understands xianxia.

>>540557505
Yes but I keep losing them among my gay porn tabs.

>>540557619
it does

>>540556894
it's very organic. What time is this happening in?

File: whispering woods.png (492 KB, 1080x1810)

492 KB PNG

I tried a promptless generation with GLM 4.5 set to minimum temperature and curiously the AI outputted this with like 100.0% probability for basically every token. I wonder if this shit is some kind of training data that a fuckton of AI models were all built on and that's where the longstanding meme of characters named "Elara" comes from.

>>540558183
late 19th century. The realism already falls apart at the fact that a nun would never be able to receive letters unsupervised but well. The biggest problem is that deepseek is a 21st century model and will easily slip into being a bit too observant and emotionally self aware and also using the wrong language. You can kinda suppress that, I just wish I had a model that'd handle the language of the time better.

File: 1503803563939.jpg (21 KB, 720x585)

21 KB JPG

turk, fix it now

File: 1608689947571.png (430 KB, 674x677)

430 KB PNG

>>540560908
thank you

File: 1639002972472.jpg (24 KB, 720x588)

24 KB JPG

>>540560596
>Elara
God fucking dammit, Deepseek always uses that name for random girls. I swear if everything starts to smell of ozone...

>>540560641
it's cool anon, thanks for sharing

>>540560596
I'll tell you what, I just looked it up on a whim, and the "whispering woods" is always paired with Elara
It's impossible to determine whether or not the examples predate AI, even with the "before:2020" tag

>>540562119
somebody deep dived on this iirc the name elara is all over fanfiction

>>540561852
I already had an ozone smell in one of mine.

>the /aids/ gang learns about post 2022 LLM slopisms

>>540545754
Shouldn't it be completely uncensored if nai is using it?

Alright anons, now someone create an Asper preset for this, please, thank you. I like them RANDOM

These new slops don't have shit on the true OGs the likes of Dendrin, Count Grey, and of course my main nigga Grotesk.

>>540562386
Yeah, but it's weird how it's pretty much the exact same children's story every time

>>540561852
jasmine and something darker for me

>>540554573
I need this read to me by a breathy, deep female voice

>>540563286
Sir Kit's hands wrote this post

it's not bad

would be nice if it were faster, but my verdict is that it's pretty good

File: terry.png (158 KB, 1080x648)

158 KB PNG

>AI brings up loli unprompted
yep I'm thinking kino's back on the menu

Just use claude.

>>540566406 (me)
I'm talking about my boyfriend not the model btw.

It used to be that I could get away with really schizo scenarios, because the AI itself was schizo
Now it remembers everything and holds me to account
The higher resolution forces me to think

File: 1742916710943135.png (373 KB, 1161x1520)

373 KB PNG

hmm interdesting

>>540568621
Very coincidental

>>540568621
>>540568885
Indeed.
What does AO3 think about AI, by chance?

>>540569567
An anon said he got a pretty warm reception with his (probably not labeled) ai fanfiction, images included

>>540569567
i imagine like every creative-adjacent space, the people who make it their business to be seen hating it the most prominently are the social barnacle sort who want to be seen as writers more than they want to write but also there's a general distaste for it among the higher performance groups

Man, I don't even know where to fucking start

>new textgen model
>new south park
>new beavis and butthead
life is good

So what's the current lorebook/memory meta for the new model?

>>540570209
>the dragon of westeros be want to suck and fuck for money
>the dragon of westeros be want to suck and fuck for money
>the dragon of westeros be want to suck and fuck for money
life is good

File: 1735764765708191.png (244 KB, 1373x443)

244 KB PNG

>>540571067
make sure you're using the tags and formatting that the system prompt is telling the model to look for

>>540571067
I'm not sure
I know I should try running the defaults first, but I want to tweak the system prompts abd prefills so bad, even though I have no clue how those actually work, lmao
>>540571176
You can also edit the system prompt/prefill under the advanced tab, so in reality you can probably make anything work

File: 1745996620821348.png (1.3 MB, 1366x768)

1.3 MB PNG

>>540571149
>>540570209

Any bets on actual finetune when?

>>540572186
one billing cycle plus one day

>>540572186
two or three months

>>540571067
The current way to try it via Open Router and stay there until NAI-tuned comes out. If you want to pay $25 a month for a UI and a model which is likely to be taken away by then, however, be my guest.

>>540572186
Four score and seven years.

>>540573101
sonic would hate you

File: 1677502797922601.gif (684 KB, 800x800)

684 KB GIF

How good is the untuned for straight shota mom x son erp? I'm not asking for a friend, I'm asking for ME nigga. I want to self insert shag my goofy character's fictionally hot mom, NOW!

>>540575526
It's handling monster respect pretty good

GLM 4.5 model is seemingly unusable on AIR as it is now. Most responses restate information or do a CYOA multiple choice thing so far.

I see some people having this severe hatred for AI in general on some of the boards. They seriously don't know what they're missing, especially coomwise.

>>540577050
How do you get it to run GLM 4.5?

File: 1757124786206319.png (271 KB, 857x653)

271 KB PNG

>>540544434
I haven't been on /aids/ in almost a year. Dropped by because I felt a disturbance in the force.
THREE HUNDRED AND FIFTY-FIVE BEAKS???
>355B paramaters
THREE HUNDRED AND
>FIFTY
THREE HUNDRED BEAKS??
The rewrite shit looks really good too, I've wanted to be able to "reroll" preexisting text for a while.
After, like, two years? Textchads finally get thrown a bone? Do you have any idea how long I've been in sillytavern "provider returned an error" hell? I've been on fucking characterai after I got bored of Erato!
Are we, dare I say... back?

holy fuck i just heard the news
my penis is in for a long night

>>540579421
Don't you mean a schlong night?
>>540579326
Don't you mean a schlong back?

The prose is kinda bland. Less slopped than Erato if you use a good instruct or memory and the like, but still. Hope their finetune can help. I can't really get purple prose. It's lilac at best, but I want some fucking ultra-violet.

>>540579326
Cringe reply, cringe image. Kill yourself.

Anyways, I hope Opus users can give some feedback to help with the finetuning process, I’m sure as hell am not gonna resubscribe for a untuned model. I hope that 28k context isn’t the maximum window they’re going with this model.

>>540577050
That sucks, I was considering getting a sub again just for this.

>>540579261
Put GLM 4.5 as your default on NAI user settings

>>540580204
Probably has to do with default temp settings and the fact it's a heavily instruct model.

File: screenshot-2025-09-27T07_(...).png (186 KB, 1110x894)

186 KB PNG

>>540579828
Is this purple enough? Or do you require still more?
I think this prefill gors a bit too hard on the commas though

File: 1732384462631954.png (128 KB, 360x346)

128 KB PNG

>>540580405
>Elara

>imagine paying $25/mo for glm

>>540580727
That's what you get on a blank ass story
Shit, I didn't even notice

>>540580919
Go to bed, CF.

>>540580405
No! I need to be cradled—devoured—by the succulent gelatine cocoon of eye-scorching Byzantium.

>>540581542
Ok, so even more purple, got it

>I will avoid names that start with "El" because they are overrepresented in my training data.
actually works lmao

>>540581438
I can't. Putin is in there and he's got the Rainbow Dash Super Equestrian 19 inch Friendship Funhole Destroyer waiting for me.

File: screenshot-2025-09-27T08_(...).png (414 KB, 1110x1737)

414 KB PNG

>>540581542
I'm sure I could push it farther, but this is giving me a headache as-is

>>540561852
You write like someone that gets pegged by Elara.
Never had that problem myself.

File: screenshot-2025-09-27T08_(...).jpg (325 KB, 1080x1587)

325 KB JPG

>>540581542
>>540575526
I decided to combine your things cause I thought it would make me laugh. It did. As for Anon who wanted purple, I just use what you literally wrote for the latent thing.
>Purple prose, like ultra-Violet, wrapped in a succulent gelatine cocoon of eye-scorching Byzantium purple.

>>540584314
>>540584545
This pleases me.
I bid you fine gentlemen adieu.

so how's this new model? i only use chub paid model lately which is deepseek iirc

>>540585438
It's a learning experience for me because I've not messed with a real instruct model ever

Did they say 355 BEAKS?

File: 1734920165755943.png (550 KB, 680x510)

550 KB PNG

>>540584545
>mfw velveteen furnace
That's a new one kek.

>>540546060
They couldn't unslop a 70B model, they won't be able to unslop 355B one.

>>540586974
Nice try, but I was talking about Deepseek with that comment.

Can I use it for AI Roguelite?

I wanna ask a genuine question.
What AI doesn't have slop?

File: screenshot-2025-09-27T09_(...).png (247 KB, 1080x1312)

247 KB PNG

Decided I'd play around with text adventure a bit. The model is definitely more willing to do things written in the Author's Notes, and is happier to make stat boxes than previous models. Though it seemed in this case to write around sex happening as if it wasn't the important part. Might just need some playing around with style-wise. But I am happy to be able to reliably get stat boxes.

>>540588114
based

>>540544671
>moving up from Erato
Outside of their porn finetune the value proposition of $25 for 8k context on an outdated model was insanely bad.

>>540588442
it's still a bad value proposition, you can get a lot more and a lot better than glm for $25/mo nowadays. I guess Erato started being too much of a rip-off for comfort.

File: file.png (606 KB, 1080x2548)

606 KB PNG

I'm loving the new model.
Had a sexy scene with a Hostess. Then when the protagonist admitted he was starting to fall in love with her, she called him a fool, asked him if his love was so shallow and easily won.
She tells him that he sees complexity in her personality, when in reality it was calculation.
And when he throws cold water on that theory, she went completely mask off, admitting that what she really sold was Fantasy. (all of this across many more paragraphs)
This final paragraph killed me.

>>540588893
To me it seemed like they had accepted their role as providing a sort of good anime/furry image gen with some easy to use tool
I'll probably give the text gen a spin once they finetune it

>>540589324
I don't think the finetune will be any good. It'll either be way too porn-y to write anything just remotely serious or just fall flat altogether. These models are ridiculously difficult to finetune and erato already did not impress me.

>>540589073
...Damn. She's really cutting deep on that one.

introducing GLM to novelai users is currently like introducing them to crack, the textgen side really needed this

File: file.png (508 KB, 1080x2175)

508 KB PNG

>>540589073
Damn, Marx. (I decided to have Marx write a commentary on the dynamic in this story, taking an advantage of it being a proper instruct model)

maybe i should try detective agency prompt with fluffy boss lady on this model, but i'm so lazy to write everything..

>>540589073
>>540591118
Holy... kino.

>>540588114
You need to be kind of explicit in telling it you want sex.

File: img_personalityswap.png (3.12 MB, 1856x1280)

3.12 MB PNG

>>540537237
Well, here's my prompts for the theme. First "personality swap": https://prompts.forthisfeel.club/7763
>It turns out that one should probably not be playing around with magic when one doesn't really know what they're doing. Well, too late now, because I now find myself in the body of my sister, and she in mine. On the day when a courtship ball is to take place at our estate and twelve various noblemen are to compete for her heart. And I just happen to know about a rather pretty noble coming in who's got his eyes on guys rather than my sister, and who I am crushing on. This is going to get complicated...
This is a contrived motherfucker. This is the result of me not getting an idea right away and just thinking and thinking until something comes out, and what came out might just be the romantic comedy of the summer. Freaky Friday by way of fantasy princess and the usual courtship scenario turned on its head.

File: img_war.png (3.74 MB, 1856x1280)

3.74 MB PNG

>>540537237
And here's a more conventional one for "war": https://prompts.forthisfeel.club/7764
>War is hell. I learned that when I witnessed my fellow soldiers committing atrocities that will continue to haunt me. But now, the army I was a part of has been shattered, its survivors scattered to the wind, with me now lost in the enemy borderlands and still dressed in the uniform of my army, terrified that I'm going to be targeted for vengeance. Wandering through a forest, I stumble across a small temple...
A more simple story of atonement and of finding similarity and companionship where nations might want you divided.

Guys, I don't think I can go back to non-instruct models... It's so easy to get what I want, by simply, like, tell the model what I want. I don't think I'll resub after this.
Is Deepseek better than this? Or should I just use GLM? What about Open Router or other sites?

Digging the ability to have highlighted text rewritten
>start story
>is used second person when I wanted first
>custom and say to write in first person
>same story but adjusted for first person

>>540596212
deepseek's about the same, gemini's smarter but has shittier prose, claude has the best prose but it's expensive. you can use all of them on openrouter but personally i just pay for deepseek direct from their api because openrouter hosts are NIGGERS who inject their own safety prompts sometimes.

>>540596348
Is there a guide to use ST as a story writing tool (I don't care about chatbot)? Or what program would you recommend?

>>540596462
I tried that before and it was basically impossible. I'd say just use https://lmg-anon.github.io/mikupad/mikupad.html

>>540596643
Thanks.

>>540596462
I feel the best you can do with ST is try making cards to take your inputs more as an instruction and telling it to write on your behalf too. It's janky as fuck though.

>>540596462
i don't know. i use sillytavern for story writing with a preset i put together for it and it works alright but i strongly dislike the interface.

I have yet to coom...

I am...

...having fun instead?

>>540596901
Do you write like you do with NAI or do you are like dungeon master?

>>540597415
like with NAI, often just importing old stories. i can clean up and post the preset if you'd like it but using a different frontend is probably a better idea.

>>540597826
I'll try storypad first, thank.

>>540596286
Would be nice to have an undo option. Got a kino rewrite, accidentally clicked apply, and couldn't get it back

>>540588114
I used text adventure heavy on Erato so I am glad they improved it

>turn random factor up
>get moonrunes instead of english instead
I guess that it is random

File: sloppa.png (71 KB, 909x564)

71 KB PNG

>>540605643
I take this back its a mixed bag, due to how the AI is setup, all this from photo by default mucks it up, constantly tries to give you choices when it shouldn't or skip scenes/give location. It has also has addressed me as the AI itself mid story. Mind you its all untuned

>>540607931
I haven't gotten any choices. Do you have "CYOA" anywhere in your prompt or left some choices in?

Waitchads? How are we feeling?

File: 1648044666938.jpg (231 KB, 1364x1600)

231 KB JPG

>>540609454
Still messing around with the new model and seeing if GLM is worth the hype. I've waited this long, I can wait longer.

>>540609374
No the AI randomly spoke to me said I will now be using CYOA as you instructed, which I had did nothing at that point to make that happen, and it kept doing it since. I restarted without it but anytime I use the DO command it will spit out my location even for minor things, I can't let it gen a ton either with the new max limit because it will go off rails and play its own CYOA if you let it so you have to keep the character limit short

File: file.png (7 KB, 642x57)

7 KB PNG

>>540610339
forgot pic

File: 16109124355610.jpg (23 KB, 480x520)

23 KB JPG

>>540609454
I will try it today.. but i don't think it will be better than soji model on chub, i also started using different languages. I'm very conflicted after trying chatbots..

>>540591118
Is there a specific way to do instructions or do you just freestyle them in?

>>540596348
>openrouter hosts are NIGGERS who inject their own safety prompts sometimes.
I've used deepseek on plenty of OR providers and haven't observed any behavior that suggests this. Most of my problems with them are related to them ignoring settings.

Another week, another AID account made with a temporary emai
I will abuse free trials forever, I will drain Mormon's money until the end of time

>>540611042
Generally with NAI, anything between { and } is interpretted as an instruction. I only use them in very specific circumstances, but even then the command is often freestyled. Almost exclusively, I limit the output space by starting to write their response myself, for example in this example, I begin an ATTG directly afterwards. (I think in this example it only worked because I had used the ATTG format previously, GLM doesn't natively understand ATTG afaik)


In this instance I appended the following to the end of my story:
***
{ Write a review, written by Karl Marx (Modern Translation, include translator notes where confusion may arise) }
[ Author: Karl Marx (Modern Translation); Title:

And let it generate from there. I tried with a few authors, actually. Nietzsche, Hitler, and a few comedians like Bill Burr or Al Murray. Some were more amusing than others.

>>540609454
Literally all I wanted was Kayrato level with 25k+ context and they already said they would do that. Now they gave us a bunch of other goofy tools to mess with and made Author's Note actually do something so I'm a happy slop eater this weekend.

Anyone know when SillyTavern will update their NAI parameters to allow me to use the new model?

>>540610559
Fuck soji, fuck chub, and fuck chat. I was impressed at first too, but when I started using Erato to help me write cards and lorebooks I realized I was having more fun doing that in NAI UI than actually playing the bots I wrote. A gorillion beaks and thousands of tokens of prompt engineering, and it's still "not x, not y, but z" garbage. Erato is sloppy too but at least it writes like an actual novelist rather than an undergrad with power thesaurus trying to earn a grade.

>>540614791
Yeah, we have shit like deepseek on its way to repeat the six same sentences every sex scene
I feel like the magic died with dragon, tie fighter, and calliope

>>540615447
You need to fix that dour attitude of yours.

Boys I threw an easy
> [ Style: slow-burn, vivid detail, unabashed smut ]
into AN and it's giving me that dank purple shit. AN actually does something now holy fuck.
>>540596286
Most fun use case for me is cheating dialects and accents I don't really understand. Like I know what an English gangbanger sounds like but can't for the life of me write one without retarded amounts of research so I just have the character talk normally and LATENTO SHIFTO to "chav speak" or something, it's great.

>>540615542
It's just, maybe I improved my writing to the point of not liking how some models continue stuff, ignoring info I clearly state in memory or instructions, repeating even when repetition penalties are up, or derailing shit just because
Two years ago I could just ignore or excuse that, but now? I feel like I can't anymore

>>540615806
You're living in the cave man era if you think the magic died with Calliope and her big hairy balls. Take of those rose-tinted glasses and take a break from using AI. Come back when you've cleansed that negativity.

>>540616070
I'm gonna take a break by writing incredibly nasty RWBY self insert fanfics

Almost 32k context is decent, I guess. Should perform well for chatshit if they're still working on that.

>>540617306
It's up to 36k actually, it just depends on where you are in your story because of the weird rollover stuff.