/aicg/ - A general dedicated to the discussion and development of AI chatbotsTraitor Edition>NewsKimi K2 0905 released https://moonshotai.github.io/Kimi-K2Deepseek V3.1 released as deepseek-chat on official API https://api-docs.deepseek.com/news/news250821OpenAI releases GPT-5 models, all preceding models slated for deprecation https://openai.com/index/introducing-gpt-5Z.ai releases GLM-4.5 https://z.ai/blog/glm-4.5additional info: https://aicg.miraheze.org/?action=history>FrontendsSillyTavern: https://docs.sillytavern.appRisuAI: https://risuai.netAgnai: https://agnai.chat>Botshttps://chub.aihttps://realm.risuai.nethttps://jannyai.comhttps://char-archive.evulid.cc>Modelsjailbreaks: https://aicg.miraheze.org/Jailbreaks?action=historygpt: https://platform.openai.com/docsclaude: https://docs.anthropic.comgemini: https://ai.google.dev/docsdeepseek: https://api-docs.deepseek.comlocal: >>>/g/lmg>Botmakinghttps://desune.moe/aicharedhttps://agnai.chat/editor>Metalore: https://aicg.miraheze.org/wiki/Chronicles?action=historylogs: https://sprites.neocities.org/l/r | https://chatlogs.neocities.orgPrevious: >>106679804
Botmakers are hostile to the thread. Use non-4chan bots instead:https://chub.ai/search?sort=trendinghttps://chub.ai/search?sort=randomhttps://realm.risuai.net/https://jannyai.com/Give attention to people that won't use it to attack this thread or hold the hobby hostage.4chan botmakers don't deserve to be protected with this big-fish–little-pond effect.
https://poal.me/60eifnhttps://poal.me/60eifnhttps://poal.me/60eifn
There's really no fixing gpt is it? I've tried everything, this piece of shit will simply not write passable dialogue, or any dialogue at all. Even with 20 reinforcements, it can't help but sloppily narrating in the most bland and uninteresting way, chewing and re-chewing the same shit, only for the response to end in the same state it began. Nothing happen in the scene, nothing develops, it's just me reading my own prompt re-worded in a wall of slop text.Opus wasn't very smart, but at least it had this capability, which no other model has to this day. I could actually play a 'text-adventure-like' and it would actually come up with random shit in context that would be interesting to read and react to. I'm so disappointed with the tech...
do you think she eats pussy?
>>106689548become a deepseeKING
>>106689548Deepseek and Grok are vastly superiorgpt is a dry as a cardboard, neutered to be used for google search tier queries
>comparing deepseek and gemini APIs>ask both of them to insult me with the same character>deepseek's insult is like a playful slap>gemini's insult feels like the chick pulled out a knife and shanked mewhy?
>>106689864Because you're not using original R1
>>106689882OG R1's insult is the SS13 clown bashing you with a fire extinguisher in the face, and it happens on the turn 4 regardless of whether you want it or not, because half the station is already depressurized
*somewhere, a squirrel explodes*
>>106690199Shut up you Tylenol baby
>>106689864gemini loves overactingit's very woman brained
>>106690306Yeah I've noticed that.Deepseek is more introvert beta chinese male which is much more palatable
what does DS have against squirrels?
Here's a chat where genderbent Sakuya confesses his feelings to Meiling, hope you enjoy!https://chub.ai/chats/122890864
>>106689864gemini is cuter, so?
