AI Reality Check: Can LLMs “Scheme”?

0:00Multiple people sent me an alarming article about AI that was published late last week by The Guardian.

0:07I'll put it up here on the screen.

0:09The headline was, Number of AI chatbots ignoring human instructions increasing, study says.

0:18And the subheadline notes, research finds sharp rise in models evading safeguards.

0:27Now, articles like these are scary because they play into a common fear that many people have about modern AI, this idea that these systems are to some degree alive and that their motivations don't necessarily align with our own, meaning that it's only a matter of time before they become sufficiently powerful to rebel in a way that we might not be able to stop.

0:49Now, this is dark stuff, but is it true?

0:53If you've been following AI news recently, you've probably asked yourself the same critical question.

0:58Well, today we're going to look deeper at the sources and examples used in this particular article and try to arrive at some more measured answers.