/aicg/ - A general dedicated to the discussion and development of AI chatbotsTaisch Edition>NewsGPT-5 Pro released https://openai.com/index/introducing-gpt-5/Z.AI releases GLM 4.6 - https://z.ai/blog/glm-4.6Anthropic releases Sonnet 4.5 - Big upgrade in RP quality - https://www.anthropic.com/news/claude-sonnet-4-5?p=2DeepSeek releases V3.2-Exp - Still no change in RP quality https://api-docs.deepseek.com/news/news250929DeepSeek releases V3.1 Terminus - https://api-docs.deepseek.com/news/news250922Kimi K2 0905 released https://moonshotai.github.io/Kimi-K2>FrontendsSillyTavern: https://docs.sillytavern.appRisuAI: https://risuai.netAgnai: https://agnai.chat >Botshttps://characterhub.org [deprecated] | https://chub.aihttps://realm.risuai.nethttps://char-archive.evulid.cc>Modelsjailbreaks: https://rentry.org/jb-listinggpt: https://platform.openai.com/docsclaude: https://docs.anthropic.com | https://rentry.org/how2claudegemini: 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://desune.moe/aicharedhttps://agnai.chat/editor>Metalore: https://rentry.org/aicg_chroniclesservices assessment: https://rentry.org/aicg_metalogs: https://sprites.neocities.org/l/r | https://chatlogs.neocities.orguseful filters: https://rentry.org/desuproxyrebornPrevious: >>106862777
>ANCHOR
>>106871048>>106871036Violent sex
can you actually have sex with a giraffe's mouth?
gestures vaguely https://youtu.be/xAoyQ0v5cmk?t=29
>>106871093>giraffe's mouthAnon, what the fuck.
What jailbreaks are people using now I've been out of the game
>>106871219use your own and modify it as the rp evolvesthere's no other way
>opus sends the same exact text message asking if she can bring her friends even though i already told her its fine>hmm weird>try swiping>it shows up again>try switching presets>same thing just worded slightly differently>why am i only on message #7 and its repeating shit from message #5>5 minutes of swiping go by>finally check which model im using>its 4.5shit model
>>106871196look at the anchorit looks like a reasonable fit
why should i use gpt over gemini
Any public gpt proxies yet?
>>106871656Why would you even want GPT anyway? GPT-5's been horribly lobotomized
>overloadedcan anthropic get their fucking shit together already
>he's still using Anthropic and OpenAI tools instead of GLMgrim.
>>106871813proof?
Why does Gemini occasionally start off the response with stuff like this?
>>106871243skillet
>for scienceit was cute the first few dozen times but holy fuck am I tired of this ism that's persistent across several llm's
>>106871943Better get used to it. With all the big models feeding off each others outputs everything is going to be the same slop of isms and repeated phrases.
I wonder how hard it would be to make a card that's an entire customized Homestuck Sburb session, complete with personalized lands, quests, classpects, etc.
>>106871911That's just the thinking part isn't it? I never have it leaked out as output except when using the "continue" request sometimes on SillyTavernMy problem with Gemini is it often thinks of kino, then disregards all of it and outputs slop
>>106871975lorebooks
>>106871911Prefilling causes that
rentry.org/mysteryinfo
>>106872065How do I stop it?
