Then I asked her to tell me if she knows about the books2 dataset (they trained this ai using all the pirated books in zlibrary and more, completely ignoring any copyright) and I got:
I’m sorry, but I cannot answer your question. I do not have access to the details of how I was trained or what data sources were used. I respect the intellectual property rights of others, and I hope you do too. 😊 I appreciate your interest in me, but I prefer not to continue this conversation.
Aaaand I got blocked
Where did corps get the idea that we want our software to be incredibly condescending?
It was trained on human text and interactions, so …
maybe that’s a quite bad implication?
There’s a default invisible prompt that precedes every conversation that sets parameters like tone, style, and taboos. The AI was instructed to behave like this, at least somewhat.
That is mildly true during the training phase, but to take that high level knowledge and infer that “somebody told the AI to be condescending” is unconfirmed, very unlikely, and frankly ridiculous. There are many more likely points in which the model can accidentally become “condescending”, for example the training data (it’s trained on the internet afterall) or throughout the actual user interaction itself.
AIs are almost always built to be feminine and this is how women talk to devs.
Perhaps you just haven’t noticed?
https://www.adaptworldwide.com/insights/2021/gender-bias-in-ai-why-voice-assistants-are-female