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
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.
I didn’t say they specifically told it to be condescending. They probably told it to adopt something like a professional neutral tone and the trained model produced a mildly condescending tone because that’s what it associated with those adjectives. This is why I said it was only somewhat instructed to do this.
They almost certainly tweaked and tested it before releasing it to the public. So they knew what they were getting either way and this must be what they wanted or close enough.
