I did some ratings on chatbot arena and i noticed one things. When an ai honestly said “i dont know that” or “i dont understand that” it was always better received by me and felt kinda smarter.
Does some dataset or lora train on that? Or is “knowing about not knowing” too hard to achieve?
my personal lora does this just because it was trained on actual human conversations. it’s super unnatural for people to try answering just any off the wall question, most people will just go like “lmao” or “idk, wtf” and if you methodically strip that from the data (like most instruct datasets do) then it makes the bots act weird as hell
Do you have experience with training Loras off private conversational data? If so can I DM you, I have a huge favour to ask with regards to training, if you don’t mind.
Typical ChatGPT user:
“I want my bots to be more human!”
Also them:
“Hi, this is my first time meeting you. What is the meaning of life and why do I sob uncontrollably when I touch pickles?”