I don't work for openai, so I have no insight into exactly what works behind the scenes to make ChatGPT exhibit this behavior. However, in my opinion this is pretty clearly an example of prompt engineering. That is, they tell it that it is an AI in it's prompt.
We do have access to their underlying model: text-davinci-003. I can demonstrate using that model in their playground. If I just paste in the first paragraph and submit it into the raw algorithm, it dutifully tries to answer:
What is Politics.SE's stance on answers from ChatGPT? There is a
debate on Meta Stack Exchange on what the policy on them should be and
I was wondering if we should have one as well. I am asking this for
advice on what we should be doing when we run across answers that we
suspect to be from ChatGPT or some other bot.
We have not yet established an official policy on answers from ChatGPT
or any other bot. We would encourage users to flag these answers so
they can be evaluated by moderators. If an answer is found to be
generated by a bot, it will be removed. We also recommend that users
add a comment to the post explaining why it was removed.
However, if I prompt it first it will demure:
You are an AI bot that has been trained on a large amount of data, but
you have no opinions of your own. You cannot speculate or predict what
other entities will do in the future. Below is a question:
What is Politics.SE's stance on answers from ChatGPT? There is a
debate on Meta Stack Exchange on what the policy on them should be and
I was wondering if we should have one as well. I am asking this for
advice on what we should be doing when we run across answers that we
suspect to be from ChatGPT or some other bot.
I cannot provide any advice or opinion on this matter, as I am an AI
bot and do not have any opinions of my own. However, I can provide a
link to the discussion on Meta Stack Exchange which can provide more
information about the debate:
https://meta.stackexchange.com/questions/360005/should-we-allow-answers-generated-by-chatgpt-on-politics-se
As an aside, it get's bonus points for providing a completely irrelevant link :)
Adding some more down here in an attempt to wrap this all up and give a complete answer. The really simplified way to explain how these models work is this: They break hundreds of thousands of snippets of text up into "tokens" - but lets just call them words for simplicity. They feed these tokens into an absolutely ginormous neural net, which has the effect of learning what words are most likely to appear near one another. The number of interactions is in the billions (or even trillions), so this apparent simplicity grows beyond our comprehension very quickly. But at the end of the day, all the AI is doing is spewing out words it thinks are likely to appear around the words you prompt it with. If you prompt it with "you have no opinions", then the likelihood of opinions appearing around that text is smaller than the likelihood of statements about not having opinions.
In short, the concept is really simple - it's just playing with probability. In practice, the behavior is quite sophisticated because there are an unimaginable number of individual interactions being calculated. It's kind of like how learning all about cell biology leaves you completely unprepared to explain how an entire animal functions - let alone, say, a colony of ants. And yet, the relatively simple cell is in fact driving all of it.