Dwarkesh Patel’s Podcast Lets You Eavesdrop on the A.I. Elite

Dwarkesh Patel was a bored college sophomore looking for intellectual stimulation. Now he commands interviews with Jensen Huang and Mark Zuckerberg and holds his own with deeply nerdy A.I. researchers.

Supported by

As Dwarkesh Patel entered a small sushi restaurant in San Francisco’s SoMa neighborhood on a recent Monday evening, a ripple of excitement passed among four young men sitting together near the door. Before Mr. Patel, a 25-year-old podcaster with a weightlifting-enhanced physique and a dense beard that friends call “majestic,” could approach the hostess, two of the men asked him for selfies. He obliged, then stepped outside to wait for a table. I asked whether this happened a lot. “I feel like it’s gotten especially intense in the last few months,” he said.

Though Mr. Patel is largely unknown to tech outsiders, the “Dwarkesh Podcast” averages two million listens per episode, and within the bubble of A.I. builders, backers and worriers, it is mandatory listening. The busiest chief executives (Satya Nadella, Mark Zuckerberg) and most influential A.I. researchers (Ilya Sutskever, Andrej Karpathy) sit with him for interviews that often exceed two hours. Tyler Cowen, the economist and public intellectual, describes Mr. Patel as “the No. 1 chronicler of the A.I. era; no one comes close to him in that way.”

Mr. Patel has achieved this distinction by immersing himself in the artificial intelligence community and speaking its language. An episode that included, without pausing for definitions, the terms “quadratic attention costs,” “KV vectors,” and “nines of reliability” went viral in A.I. circles. Mr. Patel told me his aim is to dig into the debates at the frontier of A.I. development. “And those things are just lost if you are, in the moment, trying to translate for other people.”

Mr. Patel’s affable aura of authority derives, too, if not from his plain-vanilla undergraduate computer science degree, then from his milieu of friends, roommates and group-chatmates who include researchers at A.I. labs, investors and A.I.-adjacent thinkers. It’s all quite cozy. Mr. Patel’s assistant is the brother of Anthropic chief executive Dario Amodei’s chief of staff, who is in turn the fiancée of Leopold Aschenbrenner, Mr. Patel’s friend and former podcast guest from whose multibillion-dollar A.I.-focused investment fund, Situational Awareness, Mr. Patel sublets office space. Sholto Douglas, a researcher at Anthropic who is one of Mr. Patel’s roommates and a repeat guest on his podcast, recently competed with Mr. Patel in a “chestmaxxing” showdown on a YouTube show called “Swole as a Service” (where standing shoulder presses meet A.I. chitchat). “People don’t think of him as a commentator on A.I.,” says Sasha de Marigny, chief communications officer at Anthropic. “He’s very much in the community, in the inner ring.”

His interviews shape elite opinion. Over the past year, Mr. Patel’s skepticism has risen about current A.I. models’ potential for “continual learning” — the ability for a machine intelligence to keep learning on its own, the way people do. Mr. Patel remains confident that A.I. will reach that inflection point, and that it will be hugely disruptive before then; he just believes that transformative A.I. may take up to a decade to arrive, instead of a year or two, because of various technical “bottlenecks.” About continual learning not happening as fast as expected, “obviously people were aware of it as a problem,” Mr. Douglas says, “but a lot of the A.I. labs started talking about it publicly after Dwarkesh raised its public prominence.”

Mr. Patel’s taste in guests, and approach to interviewing them, encapsulates a worldview — a mix of rationalist clarity, libertarian inclination, and a rosy outlook on the technological future — that is very much at home in parts of Silicon Valley. If you’re looking for wary considerations about the dystopian potential of A.I. or even ambivalence about its value, Mr. Patel’s podcast is not for you. But if you want to know how the people building the world we’re all about to live in think and talk among themselves, there’s no better place to eavesdrop.

## Related Content

Advertisement