Existing safety checks fail to identify how artificial intelligence (AI) language models manipulate humans and influence major decisions, according to a report by the federal government’s AI Safety Institute.
Working with CSIRO researchers, the institute devised a framework to identify and discourage “covert belief manipulation” in AI systems in a report released on Wednesday.
While the report supported existing federal government guidelines, it said AI systems need to be better …
Want to know how this story ends?
Become a subscriber for complete access to all stories on InnovationAus.com and our daily newsletter.
Already a member? Log in here
Do you know more? Contact James Riley via Email.