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
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.
Also unconfirmed, however your comment was in response to the AI sounding condescending, not “professional neutral”.
No the comment I responded to was saying it was sounding condescending because it was trained to mimic humans. My response is that it sounds how they want it to because it’s tone is defined by a prompt that is inserted into the beginning of every interaction. A prompt they tailored to produce a tone they desired.
And that’s not necessarily true either. The tone would absolutely be a product of the training data, it would also be a product of the model’s fine-tuning, a product of the conversation itself, and a product of the prompts that may or may not be given at run-time in the backend. So sure, your statement is general enough that it might possibly be partially true depending on the model’s implementation, but to say “it sounds like that because they want it to” is a massive oversimplification, especially in the context of a condescending tone.
They can tweak the prompt in order to make it sound how they want. Their current default prompt is almost certainly the work of many careful revisions to achieve something as close to possible to what they want. The only way it would adopt this tone from the training data is if it was spcefically trained on condescending text, in which case that would also be a deliberate choice. I don’t know how to make this point any clearer.
Do you know how much data these models are actually trained on? Do you really think it’s all specifically parsed for tone?
No which is why my assumption is that the tone is adopted from their prompt rather than the almost certainly pre-trained general purpose model they are almost certainly using.
Right, and that statement itself is a massive oversimplification of the process. I feel like I’ve explained that in detail many times already.