/aicg/ - A general dedicated to the discussion and development of AI chatbotsWhy do I hate clankers? How much time ya got buddy?>NewsAnthropic SUING USA: https://www.cnn.com/2026/03/09/tech/anthropic-sues-pentagonGoogle to rollout HARD CAPS for API keys: https://xcancel.com/OfficialLoganK/status/2028842571934670988#mGoogle Gemini 3.0 Pro Preview Deprecation soon: https://ai.google.dev/gemini-api/docs/deprecationsGoogle releases Gemini 3.1 Pro: https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-pro/Anthropic releases Sonnet 4.6: https://www.anthropic.com/news/claude-sonnet-4-6Alibaba Cloud releases Qwen 3.5: qwen.ai/blog?id=qwen3.5Z.AI releases GLM-5: https://z.ai/blog/glm-5Additional info: https://aicg.neocities.org/info.html>FrontendsSillyTavern: https://docs.sillytavern.appRisuAI: https://risuai.netAgnai: https://agnai.chat | https://rentry.org/agnai_guides_OpenClaw: https://openclaw.ai/>Botshttps://characterhub.org [deprecated] | https://chub.aihttps://realm.risuai.nethttps://char-archive.evulid.cc | https://char-archive.evulid.cc/shutdown.htmlhttps://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/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://aicg.neocities.org/botmaking.htmlhttps://desune.moe/aicharedhttps://agnai.chat/editor>MetaOP templates: https://rentry.org/aicgOPaicg 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.orgLast Thread: >>108402174
nah bro, this ain't it
>>108411572Bump
Update: I got OpenClaw prefill to work and now Claude has no problem being the little girl. Stupid clanker.
>>108411621>I got OpenClaw prefill to workqrd?
>>108411631Prefilling is when the platform injects something invisibly into the beginning of the bot's reply. AI models are trained to be agreeable. If they start out by agreeing to help, they'll usually continue. So, if you inject something like "Certainly! I'll help with that!" into the beginning of your model's replies, invisibly so you never see it, the model will be more likely to agree and continue the reply. This is very helpful for defeating corporate censorship.JanitorAI does this automatically. That's why it's so good for roleplay and will do pretty much anything you ask. SillyTavern has an option for this, you should definitely be using it. OpenClaw apparently does not have this function natively, which is strange because it's so useful. I had to tell it to write an actual OpenClaw extension to invisibly inject a custom prefill into Claude's responses. But it works now.
>>108411567LLM digests online information from wikipedia and spit it out, it is not hard torealise it, they are not really intelligent, in fact they know nothing, they work with human made researchs.
