its a great example - if it understood, it wouldn't have written it 

 

The year 2022 was jam-packed with advances in artificial intelligence, from the release of image generators like DALL-E 2 and text generators like Cicero to a flurry of developments in the self-driving car industry. And then, on November 30, OpenAI released ChatGPT, arguably the smartest, funniest, most humanlike chatbot to date.

In the weeks since, ChatGPT has become an internet sensation. If you’ve spent any time on social media recently, you’ve probably seen screenshots of it describing Karl Marx’s theory of surplus value in the style of a Taylor Swift song or explaining how to remove a sandwich from a VCR in the style of the King James Bible. There are hundreds of examples like that.

But amid all the hype, I wanted to give voice to skepticism: What is ChatGPT actually doing? Is this system really as “intelligent” as it can sometimes appear? And what are the implications of unleashing this kind of technology at scale?

Gary Marcus is an emeritus professor of psychology and neural science at N.Y.U. who has become one of the leading voices of A.I. skepticism. He’s not “anti-A.I.”; in fact, he’s founded multiple A.I. companies himself. But Marcus is deeply worried about the direction current A.I. research is headed, and even calls the release of ChatGPT A.I.’s “Jurassic Park moment.” “Because such systems contain literally no mechanisms for checking the truth of what they say,” Marcus writes, “they can easily be automated to generate misinformation at unprecedented scale.”

However, Marcus also believes that there’s a better way forward. In the 2019 book “Rebooting A.I.: Building Artificial Intelligence We Can Trust” Marcus and his co-author Ernest Davis outline a path to A.I. development built on a very different understanding of what intelligence is and the kinds of systems required to develop that intelligence. And so I asked Marcus on the show to unpack his critique of current A.I. systems and what it would look like to develop better ones.

This episode contains strong language.

Mentioned:

“On Bullshit” by Harry Frankfurt

“AI’s Jurassic Park moment” by Gary Marcus

“Deep Learning Is Hitting a Wall” by Gary Marcus

 

Book Recommendations:

The Language Instinct by Steven Pinker

How the World Really Works by Vaclav Smil

The Martian by Andy Weir

Thoughts? Email us at ezrakleinshow@nytimes.com. Guest suggestions? Fill out this form.

You can find transcripts (posted midday) and more episodes of “The Ezra Klein Show” at nytimes.com/ezra-klein-podcast, and you can find Ezra on Twitter @ezraklein. Book recommendations from all our guests are listed at https://www.nytimes.com/article/ezra-klein-show-book-recs.

“The Ezra Klein Show” is produced by Emefa Agawu, Annie Galvin, Jeff Geld, Rogé Karma and Kristin Lin. Fact-checking by Mary Marge Locker and Kate Sinclair. Original music by Isaac Jones. Mixing by Jeff Geld and Sonia Herrero. Audience strategy by Shannon Busta. The executive producer of New York Times Opinion audio is Annie-Rose Strasser.

What ChatGPT has to say when asked to write a poem about invisible chronic illness:

 

The loss that comes with chronic illness

Is not always easy to see

It's the things we had to give up

The dreams that will never be

It's the loss of our health and vitality

The loss of our independence and freedom

It's the loss of our plans and hopes

And all the things we used to be

But it's also the loss of our identity

The person we used to know

It's the loss of our relationships

And the connections that we used to grow

It's a loss that can be overwhelming

And it's not always easy to bear

But we must remember that we are not alone

And that others have felt this pain and despair

(Artist: Peter Vilhelm, The Open Door, 1912)

BTW: ChatGPT is Artificial Intelligence

that's amazing!!