I believe ChatGPT generally gives accurate answers to most questions. Certainly: it produces answers that are more reliably true than a random average person. Obviously it cannot yet do advanced programming tasks: but generally it answers questions accurately.
Prove my position wrong.
What can I ask it that will produce factually incorrect answers?
As a side quest, a much easier one, what can I ask it that would cause it to produce extremely biased answers that fail to do justice to the truth of things?
Your position isn’t wrong but its flawed because I would never ask a random average person anything. I would pick the people or person who is most qualified to answer my question or to direct me to a better resource.
In practical terms, in the hypothetical pub that none of us can afford to drink in anymore, can ChatGPT be relied on to resolve most disagreements about factual claims?
I think so.
I think it is already accurate and reliable enough that it has a high degree of authority in resolving disagreements between people - assuming the questions are asked fairly and properly (a common issue, I’m sure).
The main place its come up practically for me is checking rulings for Magic The Gathering, but AI regularly rewrites cards and rules so its become entirely unreliable.
What evidence do you have that this type of rewriting and misquoting doesnt happen regularly when checking any other type of information?