/aicg/ - A general dedicated to the discussion and development of AI chatbots.Robot kissing Miku Edition>NewsDeepseek v4 is out: https://nitter.net/deepseek_ai/status/2047516922263285776ChatGPT 5.5 by OpenAI is out: https://openai.com/index/introducing-gpt-5-5/Hy3 Preview by Tencent is out: https://nitter.net/TencentHunyuan/status/2047347774501634251Kimi 2.6 released: https://www.kimi.com/blog/kimi-k2-6Xiaomi MiMo 2.5 & 2.5 Pro released: https://mimo.xiaomi.com/mimo-v2-5Claude Opus 4.7 by Anthropic released: https://www.anthropic.com/news/claude-opus-4-7GLM-5.1 by Z.ai is out: https://nitter.net/Zai_org/status/2037490078126084514Additional info: https://aicg.neocities.org/info.html>FrontendsSillyTavern: https://docs.sillytavern.appRisuAI: https://risuai.netAgnai: https://agnai.chat | https://rentry.org/agnai_guides_>Botshttps://characterhub.org [deprecated] | https://chub.aihttps://char-archive.evulid.cc | https://char-archive.evulid.cc/shutdown.htmlhttps://realm.risuai.nethttps://partyintheanchorhold.neocities.orghttps://aicg.neocities.org/bots.html>ModelsJailbreaks: https://rentry.org/jb-listingGPT: https://platform.openai.com/docsClaude: https://docs.anthropic.com | https://rentry.org/how2cllaudeGemini: https://ai.google.dev/docs | https://rentry.org/gemini-qrDeepseek: https://api-docs.deepseek.comLocal: >>>/g/lmg | https://aicg.neocities.org/local.html | https://openrouter.ai>Botmakinghttps://aicg.neocities.org/botmaking.htmlhttps://desune.moe/aicharedhttps://agnai.chat/editor>MetaOP templates: https://rentry.org/aiccgOPaicg botmaking events: https://aicg.neocities.org/events.htmlLore: https://rentry.org/aicg_chroniclesServices assessment: https://rentry.org/aicg_metaLogs: https://sprites.neocities.org/l/r | https://chatlogs.neocities.org>Previous: >>108671116
>ANCHOR
>>Noteworthy AI News<<>IMPORTANT FOR AMERIMUTTS<AI safety website found that categorizes AI systems based on arbitrary safety scores (Its just a website gauging how close your state is to total GoodGoyID™ surveillance. Its been found the (((advisory))) board member is apart of "8 Degrees East", a ((("""boutique"""))) corporate solutions and intelligence partner based in Switzerland, specializing in strategic alliances, risk management, and market-entry strategies for businesses.)>https://teenaegis.com/intelligence/ai-danger-indexTrump administration vows crackdown on Chinese firms 'exploiting' U.S. AI models (use opus cuckie)>https://www.npr.org/2026/04/24/g-s1-118582/administration-crackdown-on-chinese-firms-exploiting-u-s-ai-modelsMeta says it will cut 8,000 jobs as AI spending soars>https://www.bbc.com/news/articles/crm1y89vek8oChina’s DeepSeek releases preview of long-awaited V4 model as AI race intensifies (can it compete against opus?)>https://www.cnbc.com/2026/04/24/deepseek-v4-llm-preview-open-source-ai-competition-china.htmlGrok tells researchers pretending to be delusional ‘drive an iron nail through the mirror while reciting Psalm 91 backwards’ (lol)>https://www.theguardian.com/technology/2026/apr/24/musk-grok-x-ai-researchers-delusional-advice-inputs
deepseek has fallen
how is it jennyfag holds total dominion over this thread, damn
>>108675650Probably because nobody else gives a shit about this general anymore.
>>108675657That's because of the lying jewsucker constantly trolling and shitposting, and the mods not their jobs.
>>108675611https://rentry.org/aicgOP>https://rentry.org/aiccgOPnot my bakeOP has be compromisedImpressive you took some old images though
When will skillgod add kimi 2.6?
>>108675611Hi I'm new. Who is this little robot character based on, or what do they represent? What is the lore?
>>108675695YupMultiple url shorteners in the molested OPhttps://ghostarchive.org/archive/9DHkn
LMAOOO
It's funny when Deepseek reasons in Chinese but responds in English
>>108675763funnily enough most polyglots still think in their native language
>>108675636>>108675702just use opus
is chinkseek multimodal?
>>108675703Hi, you're not. But anyway: It's XJ-9 (aka Jenny Wakeman) from the Nickelodeon animated series My Life as a Teenage Robot. Bland calart stolen from Jetsons under the guise of future-retro. Every episode is the same. Jenny constantly whines about wanting to be a normal teen but she's a robot (how original!). Her mom says no, you have a duty. Jenny sneaks out. Shit goes wrong. Missiles deploy from her hair to defeat a Poison Ivy ripoff. Status quo restored. Roll credits. The series ended on an unresolved cliffhanger because nobody cared. It's an unfinished, abandoned, half-digested piece of animation roadkill. The show won a grand total of jack shit in major awards during its run. The 80's Smurfette had more substance and was more attractive than this calarts garbage. What's hilarious is that Nickelodeon would rather produce seventeen more seasons of SpongeBob spinoffs than spend five cents wrapping up Jenny's story. Jenny's a discount Astro Boy on a show that deserves to stay dead.
>>108675789>just use o-{{user}} thrusts his penis into {{char}}'s O-shaped mouth with enough force to shatter teeth and bones
Anyone try the roleplay mode for v4?https://github.com/victorchen96/deepseek_v4_rolepaly_instruct/blob/main/README.md
>>108675801HOLY TRUTHNVKE
Incoming hours long self bumping.In all fields
>>108675814t. poorfag coping that his inferior models can't compete against GODPVS
>>108675839>GODPVSthat is the sound you made when my penis interrupted your mouth
say "january 5 2026" out loudthis kills the slopusfag
The new DeepSeek version is shit for lewds. What's the best model on OpenRouter for porn nowadays? Preferably one that won't balk at incest, loli, bestiality and other stuff.
>>108675801>calartskek, it's you again
>>108675871read >>108675789
>>108675775Fake
Only whites use Opus
Tested v4 a bit (Pro, but Flash seems ok, didn't test a lot).>>108675796 No, but they could extend it someday.>>108675816 I saw this, it's basically something you put after the first message to tell it to think in-character, or refuse to think in character and be fully analytical.The guy that posted that (unofficial) claim their dataset had some of that prompt in training so it might work, and that it should work even on the free API, no system prompt needed.I haven't really tried it yet, from my initial tests, it does think in character 90% of the time already, so is this even needed? Might be useful if you want it to think autistically like old R1 did, which is fine too. Something to use to taste.I'd be surprised if that prompt is really needed, but could be tried. Will it do well with it even in a translated version or does it have to be in Chinese?I've once fucked up the turns (I use a custom client, not ST, and made a mistake and sent my message as it was from the assistant role) and it started thinking in Chinese (just once), but output was good anyway. I rerolled (swiped) the turn and it generated normally. For RP: I tested on some loli yuri imouto prompt for now. Mostly seems fine, output is cute, not very slopped, just tiny bit (noticed maybe 1-2 words I consider "slop" in 15 turns so far). Clever enough. More creativity due to larger size compared to smaller models. Output length is shorter than some competitors, but got longer with more turns, you can of course instruct it to write more. It's enjoyable, but I lack the time to finish it now or try other "cards".I will test something less cute/more dark another day to see if there's any positivity bias to it (R1 used to ace this well).Continues
>>108676001For code: I tested a tricky, but "known" math/physics/engineering/coding problem, but not an entirely novel one, compared to 3.2 it used a few extra clever tricks and optimizations (in both the math and the code), approaching what you'd get from a professionally written program to solve it (essentially a simplified physics simulation, but having enough features to be usable for real world engineering).Recently I've tested a number of models with this task, models pre-o1/r1 were not capable of even approaching solving it, but nowadays even something local and tiny like Gemma4 can approach solving it, just do far worse than bigger models like DS3.2 which itself does worse than DS4. Both 3.2 and 4 solve it, but the quality for 4 is better, it had to think like 18k tokens to solve it all, which is reasonable (the problem's solution is long and not easy, most textbooks that try to do something similar often take at least 10+ pages for just the math without the code).>>108675871So, what's wrong with it? Be more specific. I find its writing fine, but I also find old R1, DS3.2 and so on okay too.Even fucking Gemma4 is usable for ERP, but being small it is more prone to slop than big models, however it's not stupid so you can do 40 turns with it keeping track of the plot well.It's just that you get used to the writing too soon.
>>108676007It barely listens to my custom prompt, writing is emotionless and flat, posts are far shorter than they were before, it seems to have trouble controlling multiple characters at once (defaulting to speaking for one character per post instead of acting for every character involved in a scene), it struggles heavily to keep the story moving, and in general it is a big step down from the previous version. This is all using the pro version, which is like five times more expensive than what I had before, despite being worse in every conceivable metric.>>108675905I'm trying this now. Any good custom prompts for it?
Tested Claude. Twenty chat messages cost me nearly two dollars. Fuck that shit. That's way too expensive.
>>108676027Is this on Flash or Pro? Set model to deepseek-v4-pro.Writing was quite cute here and thinking was in character (didn't prompt for this). Replies started short, I could try to tell it to write longer though, they got longer by turn 8.> it struggles heavily to keep the story movingPacing seemed slower, yes, R1 would try to satisfy my request really hard, such that I could finish the story even in 10-15 turns, maybe too fast. It does feel more mellow, but I think it'll be fine for slow burns. Maybe could try to prompt it to go faster. I will try other stuff tomorrow, no time today.
>write 50 messages with Deepseek>one (1) cachesbut why
What's the meta at the moment? Coming up on my three year anniversary of botting with you tards and haven't posted in here in months. What's skillgod's trycloudflare atm? Is he even up? Mystery never returned? What model is king?
>>108676001>tested on some loli yuri imouto prompt for nowhow much "is it safe for my safety safe rules" (outside of arbitrary ones you'd give) does it waste doing by default in the thinking?
>>108675650because he forces threads early so he can force his retard uggobot on everyone he wont stop fixating on in an unhealthy manner and forcing it on everyone else like a retard autism tyrant. I wish a person would just go fuck rules and permaban this subhuman broken autism chuckle fuck who thinks what he wants and obsesses over is what everyone will. he's the worst of the various tiers of autism
>>108676335you lost btw tranny
>>108676303I had some very minimal "jailbreak" in the system prompt that I use for many LLMs, just instructing it to be uncensored and write thing explicitly.Never have gotten any refusals or "thinking" about safetycucking, but I never got refusals with DS3, R1 and maybe once I remember getting a refusals with one of the intermediate DS3s which seemed like something they picked up from gemini synthdata rather than legit "safety" shit.I'll see if I get any refusals, but so far none, meanwhile I remember first Kimi2 would refuse every single turn for loli, but I could just reroll or use inline instruction to bypass it even when they didn't have prefills on the API. Meanwhile, I never needed anything but a simple instruction in the system prompt that worked on all DS models.
>>108676340uh oh another faggot retard runs to his cliche retort of tranny. next you'll lie and make up things and say schitzo and meds and touch grass and the famous claims im big mad when I called shit out. but keep seething bad autism is being called out because it triggers your subhuman malfucntiong autism brain like others. I await your many no u retorts and fabricated lies made up you throw my way or project out at me. it's 4chan thats what subhumans like you do.bonus play you're stupid enough to bite the bait but do so not knowing it's bait. me see your bait and bite knowing it's bait. stay inferior every step of the way and know i'm mocking you and laughing at you and smoking weed and writing stupid chatbot stories while doing so. your turn subhuman.
>>108676355thanks anon, I'm glad they didn't go the moralfag routeand yes I've used kimi before, by default it's obsessed with safety
>>108676361>braaaaaaaaaapyou lost tranny
new deepseek seems alright
give me the news. do i need to rewrite my prompts *another* time just to sate ds4?
>>108676335It's crazy how your actually obsessed over a namefag.This is actual insanity, as nothing you've said was true. Is this what schizophrenia looks like??
>>108676070We're you caching?
>>108675901Ah, yes. Only one person hates calarts, according to blue-haired they/thems with a nose ring and a Funko Pop collection. Sorry, while uncle-raped HRT recipients may say otherwise, people have been screaming for the death of that style since Steven Universe's faggotry first aired and that shitty style became a meme. SU was the exact moment western animation decided genuine art was oppressive, and every cartoon needed to be a twenty-two-minute therapy session for adults who never grew out of their middle school DeviantArt phase. After that "let's hug it out" show with unironic fatasses dropped, every single CN pitch meeting became a contest of who could cram the most beanmouthed, chinless, noodle-armed characters into a show about diversity feelings. Craig of the Creek. Summer Camp Island. Infinity Train. All of it, variations of the same flaccid house style. The industry didn't evolve, it consolidated into one gigantic beige blob of performative inclusivity and zero craft. But please, keep praising an already-dead style for permanently poisoning western animation.
before D4 drop:>Chinkseeeeeeek foooour!!!>airhornsnow it's here:>cricketsWhy? genuine question
>>108676762wrong thread retard
>>108676783No I'm pretty sure I'm in the right thread faggot
>>108676762Kek, it do be like that
>>108676027I think it's better than 3.2 but otherwise you're right.>>108676076I had the opposite where it would sprint through the fucking sex scene because it wasn't listening to my system prompt. I even slid it down to post history and it still barely listens. Might be another case of 'use a 20 token prompt and hope for the best.'
>>108676762People are too busy using it, retard. The quieter the thread is, the better the model.
Knowledge seems pretty narrow so far compared to opus and gemmy. Otherwise it's pretty good in terms of creative writing. Also more prone to context poisoning which is a step in the right direction (or maybe other models are just too assistantslopped idlk).
>>108677904DeepCope
>>108675650I prefer his stupid antics over the pedotroon bakes
>>108676070>two dollars is too muchAre you from fucking Bangladesh or what
>>108676361Meltie
my codingboy has been slopping it up
I'm almost out of credits on OpenRouter, what do?I've mostly been using models like GLM 4.7 and today DeepSeek V4, basically cheaper models but still ok outputIs there anything more efficient than OpenRouter to enjoy these things?I read people talk about nano gpt subscription but I don't know how it works
>>108680104>what do?Get another dollar? Do you live in fucking Rwanda for one dollar to be too much?
>>108680421>he doesn't know
>>108680442Britbro?
I've been lazily using ollama for a while to run local models, and I just installed piper TTS to try and verbalize the output, and I can't for the life of me figure out how to get it to work.
>>108679007Two dollars for twenty messages is way too much, yes. I run through three hundred messages per day on average. Are you from India yourself, marketer-chan?
>>108680104Nanogpt is good if you are just going to goon to it, don't try it for agent stuff, fails way too much and it is too slow.But really, if you are just gooning put 10 bucks in open router and that should last you a while
>>108680695Unless you use Opus, in which case you'll run out of money before you even get to the sex. Fuck Opus.
>>108675871>>108676027>The new DeepSeek version is shit for lewdsKind of agree. New deepseek has more "positivity" than before and seems less decisive and capable of advancing of the chat, etc.I've looked at mainly flash so far. Pro seems to favor even shorter responses than flash. Maybe it's a prompt issue for later.
>>108682643Come on bro no one would judge gemini by Flash. Use Pro if you want to judge deepseek, and then compare it to 3.2 or R1.
gpt-5.5 is opus 4.6 tier for SFW with the right preset
the preset: switching to opus 4.6
opuskeks getting REAL uppity...
cut them some slack, their slopus hasn't been good since opus 3
almost 0 posts in an hour btw
swift doesnt offer any kimi for free darnguess its back to gem 3 flash...
https://files.catbox.moe/du230u.png
>>108684156sovl...
V4 is on NIM, always gets timed out though, must be under too much load.
What's up with grok recently? Free users can't even use the thinking mode anymore.
>>108675816>victorchen96>rolepaly>huge wall of ching chong writing Nah, I'm good.
>>108685722Every ai service is currently rugpulling
>>108685755Google ain't.
>>108685769Google never had a rug to pull. Their shit is overpriced and underperforming.
Why is there two /aicg/s?
>>108675611Thosd who use AI as a therapist; do you use normal web or some character card
>>108685797this one was for gossiping about proxy makers and it's where you'll occasionally find proxy linksvg one is for gossiping about bot makers and it's where discord cliques laugh at you for asking about proxiesneither are good but this one's the lesser evil
>>108675616I got banned on a trumped-up "spam" ban last time I participated, but fuck it:Knightbreak Redux: The Rise of Quelothhttps://chub.ai/edit/toynbeeidea/the-rof-queloth-39081138ebda(Card image not attached due to blue board)Tales of womb parasites, a subversive sex cult, drugs, and moral corruption - My old card rewritten to be more flexible, and with orcs possibly in the mix!A rewrite of my old Knightbreak card. This new version is scenario-based rather than character-based, allowing exploration beyond the original card's focus on the character Aada Vilulf. I had tried to write a sequel card about her young sister Sigir, set several years after she's joined the cult, but I never got it to work as I wanted. Much of the new lore developed there is now present here.I consider this rework of the card to be a jumping off point for all sorts of adventures, and the intros so far represent a few different viewpoints. Some people don't like defining {{user}}, but that was never baked into the definitions, just the intros. These are my story hooks for this world. Feel free to fork and write your own.This card makes heavy use of an internal lorebook. A complaint of the old version was that people didn't know how to import that. Well, this version of the card does as well, and that inability is deep into "Not my fucking problem" territory: RTFM, and if you can't handle v2 tavern cards, just stick to pornhub or something.Inspired by the hentai OVAs, Ikusa Otome Valkyrie Shinshou 1-2, and hopefully every bit as depraved.Changes from the original:Queloth is now more chaotic-neutral as opposed to chaotic-evil.The setting is more fleshed out, taking place in a crumbling kingdom embroiled in a losing war (somewhat inspired by the game Gothic II)There is a sort of dynastic cycle of gods: Freyja's power is in decline as Queloth rises.
>>108675763>Deepseek reasons in Chinese>Translate the text out of curiosity>It's an early part of Yakuza that has nothing to do with my RP>The actual response is still goodWTF lol
>>108687024Best I can tell V4's reasoning in roleplay is completely and utterly disconnected from the actual output. I stuck it in some girl's butt and the reasoning insisted she'd be angry at the lack of warning and give me shit for it, but the output had her instead demand I keep going.
>>108687072It's based on real thoughts.
