When one logs on to Chat GPT, they get the following notices:
> This is a free research preview.
> Our goal is to get external feedback in order to improve our systems and make them safer.
> While we have safeguards in place, the system may occasionally generate incorrect or misleading information and produce offensive or biased content. It is not intended to give advice.
> Conversations may be reviewed by our AI trainers to improve our systems.
> Please don't share any sensitive information in your conversations.
Effectively no guidance or instructions indeed. Perhaps ChatGPT is sometimes confidently incorrect because it learned from online commenters.