Latest / What's Your Problem? / Teaching Cars to Think Like People

Transcript

Teaching Cars to Think Like People · What's Your Problem?

• 0:15
  Speaker 1: Pushkin. It seems like we've been hearing for I don't
• 0:22
  Speaker 1: know ten years now that self driving cars are two
• 0:26
  Speaker 1: years away. And yes, I know Tesla's are amazing because
• 0:29
  Speaker 1: Tesla owners keep telling me so. But we are clearly
• 0:33
  Speaker 1: not yet at that magic transformative moment when cars can
• 0:37
  Speaker 1: truly drive themselves. We're not yet in a world where
• 0:41
  Speaker 1: a human driver seems as out of place as a
• 0:44
  Speaker 1: human elevator operator. So the question for today's show is this,
• 0:49
  Speaker 1: what is the most important problem that we have to
• 0:52
  Speaker 1: solve for that to happen. What's it going to take
• 0:55
  Speaker 1: to get to a world where I'm heading north on
• 0:57
  Speaker 1: I five and I just climb in the back of
• 1:00
  Speaker 1: my car and take a nap. I'm Jacob Goldstein, and
• 1:05
  Speaker 1: this is What's Your Problem, the show where we talk
• 1:07
  Speaker 1: to entrepreneurs and engineers about the future they're going to
• 1:10
  Speaker 1: build once they solve a few problems. My guest today
• 1:14
  Speaker 1: is Aisha Evans, CEO of the autonomous car company Zooks
• 1:18
  Speaker 1: zoo X. Zooks was acquired by Amazon back in twenty twenty,
• 1:23
  Speaker 1: and I wanted to talk to Aisha because Zooks is
• 1:25
  Speaker 1: really all in on this self driving car dream. They're
• 1:29
  Speaker 1: not going for half measures. They're not going for baby steps.
• 1:32
  Speaker 1: They're trying to build a truly fully AI take the
• 1:36
  Speaker 1: wheel self driving car. So I should seem like the
• 1:40
  Speaker 1: perfect person to talk about the problems engineers are going
• 1:43
  Speaker 1: to have to solve to build a car that can
• 1:45
  Speaker 1: truly drive itself. We started our conversation talking about the
• 1:51
  Speaker 1: self driving car that Zoos is building now, which really
• 1:54
  Speaker 1: isn't exactly a car. It looks like a toaster on wheels.
• 1:58
  Speaker 1: It's very boxy. There are sliding doors on either side,
• 2:02
  Speaker 1: and inside there are two bench seats facing each other,
• 2:06
  Speaker 1: and that's kind of it. There's no driver seat, there's
• 2:10
  Speaker 1: no dashboard, there's no steering wheel. If you step into
• 2:15
  Speaker 1: our vehicle and you think about driving, we consider that
• 2:19
  Speaker 1: we failed what transporting you no pedals, no steering wheel,
• 2:23
  Speaker 1: You are not involved in the driving. You're a rider,
• 2:25
  Speaker 1: and we conceived it for you. There's also no front
• 2:29
  Speaker 1: or back right, no fully symmetrical. When you think again
• 2:33
  Speaker 1: about the effectiveness and the efficiency of transportation, especially in
• 2:37
  Speaker 1: dense urban environment, imagine pulling into a narrow alley and
• 2:41
  Speaker 1: not having to make a U turn and just flipping
• 2:43
  Speaker 1: the lights and the vehicle goes into the other direction.
• 2:46
  Speaker 1: So the thing I like about it, not having a
• 2:48
  Speaker 1: steering wheel, not having a front or back is just
• 2:51
  Speaker 1: the way the thing looks. The physical thing itself is
• 2:56
  Speaker 1: this manifestation of how all in you are. Right. It's
• 3:00
  Speaker 1: not like, let's take a car and make a robot
• 3:02
  Speaker 1: drive it. It's what does the world look like? What
• 3:05
  Speaker 1: does a thing look like if there is no driver? Yes,
• 3:08
  Speaker 1: if you you know, you become dispassionate no matter what
• 3:12
  Speaker 1: car you have today, a personal car, and you look
• 3:15
  Speaker 1: at it purely from an engineering standpoint. It's architected and
• 3:19
  Speaker 1: designed with the concept of a human driver. Yea. What
• 3:24
  Speaker 1: we're doing, by the way, is really okay. If AI
• 3:28
  Speaker 1: is going to be responsible for the driving amongst other
• 3:32
  Speaker 1: human drivers, how do you architect and design the vehicle
• 3:38
  Speaker 1: so that AI is the best and safest drival possible.
• 3:43
  Speaker 1: That's our point of view, and then you work backward
• 3:45
  Speaker 1: from there. So so how's it going to work? Basically,
• 3:51
  Speaker 1: you have the app, you say I want to go
• 3:53
  Speaker 1: from here to there. We come, we pick you up,
• 3:55
  Speaker 1: you sit down, you buckle up, push start. That's a
• 3:58
  Speaker 1: safety thing, and then we take you to point B
• 4:02
  Speaker 1: and your unbuckle, step off, and by that time we
• 4:05
  Speaker 1: probably already know the other passenger. When can I call
• 4:09
  Speaker 1: one depends on where you are. So if you're in
• 4:13
  Speaker 1: Las Vegas fairly soon, much sooner than you think on
• 4:17
  Speaker 1: the strip, you'll be able to call one. Does that
• 4:19
  Speaker 1: mean this year? Next year? It won't be this year.
• 4:24
  Speaker 1: I can tell you what happened by twenty twenty five. Yes,
• 4:29
  Speaker 1: And once we do that, then we'll go city by city.
• 4:32
  Speaker 1: We've already been public saying that we'll go Las Vegas
• 4:36
  Speaker 1: and then San Francisco. Then as we want to move east,
• 4:40
  Speaker 1: but then as you're moving east you have to handle snow.
• 4:43
  Speaker 1: And then we want to be global, and as you
• 4:46
  Speaker 1: go global, you get a whole new set of parameters.
• 4:49
  Speaker 1: The roundabouts in London come to mind, and so is
• 4:53
  Speaker 1: the idea that zoos vehicles will be like cabs are. Now,
• 4:58
  Speaker 1: like I have a car, and then if I'm in
• 5:00
  Speaker 1: the city and I need to get from one place
• 5:02
  Speaker 1: to another, maybe I'll take a cab. Is it like that?
• 5:05
  Speaker 1: It's like that with a little bit deeper philosophy, which is, look,
• 5:10
  Speaker 1: we know that let's not with the United States, right,
• 5:13
  Speaker 1: it's around two and a half cars roughly per family.
• 5:17
  Speaker 1: We're not saying it'll be zero overnight, obviously you have
• 5:19
  Speaker 1: to be rational, but we can do better than two
• 5:22
  Speaker 1: and a half cars per family. So let's say we
• 5:25
  Speaker 1: get to one or one and a half. We feel
• 5:27
  Speaker 1: that we will have done something after the break. The
• 5:31
  Speaker 1: technical problems that Zoos and for that matter, all the
• 5:34
  Speaker 1: other self driving car companies are still trying to fix.
• 5:38
  Speaker 1: One surprisingly hard one, how to figure out who goes
• 5:41
  Speaker 1: first when two cars pull up to an intersection at
• 5:44
  Speaker 1: the same time. I should calls it the UGO I
• 5:47
  Speaker 1: goo problem. Now let's get back to what's your problem. So, Okay,
• 5:54
  Speaker 1: the world has been talking about self driving cars for
• 5:57
  Speaker 1: well over ten years now, and we know that to
• 6:00
  Speaker 1: get to this self driving car world, there's going to
• 6:02
  Speaker 1: be regulatory hurdles. There's going to be people worried about safety.
• 6:05
  Speaker 1: I feel like all of that is pretty familiar by now.
• 6:08
  Speaker 1: The thing I really wanted to talk with Aisha about
• 6:11
  Speaker 1: is the technical side. You know, like, what problem exactly
• 6:15
  Speaker 1: do engineers have to solve to build cars that can
• 6:18
  Speaker 1: really drive themselves. All of the companies can drive, and
• 6:23
  Speaker 1: the normal very kind of constrained circumstances, The thing is
• 6:28
  Speaker 1: all of these scenarios that can pop up, how do
• 6:30
  Speaker 1: you deal with them? And by the way, how do
• 6:32
  Speaker 1: you deal with them knowing you have human drivers around you,
• 6:36
  Speaker 1: they have their own learned behaviors and learned expectations as
• 6:41
  Speaker 1: to what's going to come from a human driver. And
• 6:43
  Speaker 1: the etiquette, the etiquette of it too that will not
• 6:47
  Speaker 1: fully there yet. Tell me about the etiquette, Well, depending
• 6:50
  Speaker 1: on which parts of the city, like if you're in
• 6:53
  Speaker 1: more of a neighborhood area versus more of a business area,
• 6:57
  Speaker 1: the behaviors are slightly different in how you approach things.
• 7:00
  Speaker 1: So for example, we call it Ugo I goo. The
• 7:04
  Speaker 1: ugo igo is a little bit more assertive on the
• 7:06
  Speaker 1: business side of things versus in a place where that's
• 7:09
  Speaker 1: a little bit more residential. So all that is again
• 7:13
  Speaker 1: the long tale of scenarios that we have to deal
• 7:16
  Speaker 1: with and be ready for. The you go, I go
• 7:19
  Speaker 1: is a really interesting one because that's not about the
• 7:23
  Speaker 1: formal like rules of the road, right, that is very
• 7:27
  Speaker 1: much a cultural thing that's gonna even vary from town
• 7:31
  Speaker 1: to town. Right. I've lived different places and you go,
• 7:34
  Speaker 1: I go. It's totally different in you know, Brooklyn than
• 7:37
  Speaker 1: it is in Bozeman, Montana, So like, how's an AI
• 7:41
  Speaker 1: going to figure that out? This is where training is
• 7:44
  Speaker 1: important because before it'll be a long, long, long, long
• 7:48
  Speaker 1: time where you just deploy what we call generic AI,
• 7:52
  Speaker 1: which is you come in for the first time, you
• 7:54
  Speaker 1: drop in and boom, you know how to do it.
• 7:56
  Speaker 1: So a lot of a lot of what we do
• 7:59
  Speaker 1: is learn and train, and that's why you know it's
• 8:01
  Speaker 1: called deep learning for example. And so we do it
• 8:04
  Speaker 1: enough times enough forms that the stack knows what to
• 8:09
  Speaker 1: look for to make the call. And we have those
• 8:11
  Speaker 1: examples today. For example, how we drive in San Francisco
• 8:15
  Speaker 1: versus how we drive in the campus were on today,
• 8:18
  Speaker 1: it's totally different. We're a lot more assertive in San
• 8:22
  Speaker 1: Francisco because that's what's expected. The buffers are smaller because
• 8:27
  Speaker 1: that's also what's expected than we do on the campus.
• 8:31
  Speaker 1: So all that is built into the stack, both with
• 8:33
  Speaker 1: control logic as well as with algorithms logic based on
• 8:38
  Speaker 1: our training models. So I'm trying to sort of boil
• 8:42
  Speaker 1: down what you're saying. I mean, it's interesting, like on
• 8:44
  Speaker 1: a certain level, you're saying you've solved the kind of
• 8:47
  Speaker 1: big macro technical problems for computers to drive cars basically,
• 8:53
  Speaker 1: But you're also saying there are a million edge cases
• 8:57
  Speaker 1: double parked cars and bikes doing weird things, and who knows,
• 9:02
  Speaker 1: people are weird, The world is weird, and those you
• 9:06
  Speaker 1: haven't solved exactly. You're just saying you just have to
• 9:09
  Speaker 1: practice more to get it. You just have to do
• 9:12
  Speaker 1: it like that. Why am I unsatisfied by that answer?
• 9:15
  Speaker 1: Because it's to be fair, you have to practice. But
• 9:19
  Speaker 1: practice is a feedback loop of doing yeah, finding errors
• 9:25
  Speaker 1: and figuring out how to deal with the errors, doing
• 9:28
  Speaker 1: it again. So it's a continuous feedback loop of that,
• 9:31
  Speaker 1: and that is what is left to solve. Can you
• 9:34
  Speaker 1: give me an example of a version of that loop
• 9:36
  Speaker 1: you've just completed where you found an error and then
• 9:39
  Speaker 1: fixed it. What's an example of that? Yeah, this one
• 9:42
  Speaker 1: is very personal. My first Zooks ride ever, So that's
• 9:48
  Speaker 1: three and a half years ago. When the vehicle saw
• 9:51
  Speaker 1: a double parked vehicle in front of it, but there
• 9:56
  Speaker 1: was it's a single lane and so you have basically
• 9:59
  Speaker 1: a double yellow line. The vehicle says, oh, the rule
• 10:03
  Speaker 1: says through the AI stack that I cannot cross a
• 10:07
  Speaker 1: double yellow line. Right, We would actually stop, disengage and
• 10:12
  Speaker 1: do it manually and go around it. But over time
• 10:16
  Speaker 1: we've now learned through all of the dpvs we've seen,
• 10:19
  Speaker 1: and so there are many times now when the app
• 10:23
  Speaker 1: is a vehicle, ye sorry, when when there's a double
• 10:28
  Speaker 1: park vehicle in front of the vehicle. Now the vehicle
• 10:32
  Speaker 1: is able to look through the sense of pod, look
• 10:34
  Speaker 1: at oncoming traffic, look at everything else, speeds and feeds
• 10:39
  Speaker 1: and everything else around it, and many times now it
• 10:42
  Speaker 1: is able to just smoothly like a human would do,
• 10:46
  Speaker 1: make the decision itself. That's a good one because there's
• 10:48
  Speaker 1: a clear rule you can't cross a double yellow line.
• 10:51
  Speaker 1: We all learn that. But yeah, we also all know
• 10:53
  Speaker 1: if you're driving along and somebody's double parked in front
• 10:55
  Speaker 1: of you, got to swerve over and nobody's coming the
• 10:58
  Speaker 1: other way, like you're allowed to do that exactly. So
• 11:00
  Speaker 1: how does an AI figure out when it's okay to
• 11:03
  Speaker 1: do that? So we through again the algorithms, through a
• 11:07
  Speaker 1: lot of training, meaning all the scenarios. If it's seen
• 11:11
  Speaker 1: over and over again, it's able to say, okay, I looked.
• 11:15
  Speaker 1: And this is where again the placement of the center
• 11:17
  Speaker 1: architecture is very important because in our vehicle. Since it's
• 11:20
  Speaker 1: every top four corner and you have a two hundred
• 11:23
  Speaker 1: and seventy degree view, it's able to basically say, hey,
• 11:26
  Speaker 1: I'm looking in front of me. I have plenty of space.
• 11:28
  Speaker 1: There's no car coming on the oncoming lane, and I
• 11:31
  Speaker 1: see that I have space. Also in front of the
• 11:34
  Speaker 1: double park vehicle, there are no pedestrian, there's no bike
• 11:38
  Speaker 1: coming up. Oh yeah, I can do this. It goes ahead.
• 11:41
  Speaker 1: So you're telling me, basically, like the AI, the machine,
• 11:44
  Speaker 1: the vehicle already knows how to drive. It just needs
• 11:46
  Speaker 1: to practice, just needs to practice for millions of hours.
• 11:50
  Speaker 1: It's funny you should say this. I have a sixteen
• 11:52
  Speaker 1: year old daughter, so she started the journey of driving,
• 11:55
  Speaker 1: and you know, at first we were just within a
• 11:58
  Speaker 1: mile of the house in the neighborhood, then maybe some
• 12:02
  Speaker 1: areas where they are stop signs, and now we're up
• 12:05
  Speaker 1: to a sort of the supermarket, and very soon we'll
• 12:08
  Speaker 1: be up to going to school. It is the case
• 12:11
  Speaker 1: that human beings can learn to drive pretty well in
• 12:16
  Speaker 1: like what forty hours or so, and computers clearly cannot. Right.
• 12:24
  Speaker 1: And I used to think people were bad drivers, right,
• 12:29
  Speaker 1: Like it seems obvious to me frankly, that people are
• 12:32
  Speaker 1: bad drivers, right. You know, we look at our phones
• 12:35
  Speaker 1: while we're driving. We overrate our driving abilities. We have
• 12:38
  Speaker 1: literal blind spots. On the other hand, zooks, vehicles can
• 12:43
  Speaker 1: see way better than people can see all the way
• 12:45
  Speaker 1: around in three hundred and sixty degrees. They have like
• 12:48
  Speaker 1: the smartest people in the world trying to teach them
• 12:51
  Speaker 1: how to drive. They have millions of hours of practicing,
• 12:54
  Speaker 1: and still they're worse than human drivers. So, like, I
• 12:58
  Speaker 1: don't know how to parse that, right, Like, are people
• 13:01
  Speaker 1: actually way better drivers than I thought? Well, so I
• 13:05
  Speaker 1: think that we conflate a lot of things when we
• 13:08
  Speaker 1: talk about driving. So let's go back to my daughter.
• 13:11
  Speaker 1: I don't think I dispute a little bit that my
• 13:14
  Speaker 1: child started learning to drive at sixteen. She started learning
• 13:19
  Speaker 1: to drive the first day she was in a car, Yeah,
• 13:22
  Speaker 1: or maybe even the first day she was alive. That's
• 13:25
  Speaker 1: my seeing physics and seeing the world and understanding people.
• 13:30
  Speaker 1: I mean, that's maybe the most interesting thing for me
• 13:33
  Speaker 1: in this conversation, right, is like the hard part in
• 13:36
  Speaker 1: teaching computers to drive is teaching them to figure out
• 13:39
  Speaker 1: people exactly. And ecosystems that are built around and four people.
• 13:45
  Speaker 1: That in a way is the ultimate problem you're trying
• 13:47
  Speaker 1: to solve, right, Like try and teach a computer to
• 13:50
  Speaker 1: think like a person. That's exactly right. And I think
• 13:54
  Speaker 1: when I put my firstborn in the car seat coming
• 13:58
  Speaker 1: home from the hospital, she was already starting to learn huh,
• 14:02
  Speaker 1: say more. You know you're in a car, you know
• 14:05
  Speaker 1: it's moving, you know there's a driver, your parents, you're
• 14:09
  Speaker 1: looking around you. You're already starting to your internal algorithms
• 14:13
  Speaker 1: are already starting to learn and take inputs. You know
• 14:16
  Speaker 1: that you need to stop at a light before you're
• 14:18
  Speaker 1: an actual driver, right, and then all of the weirdness
• 14:22
  Speaker 1: of like if somebody is nodding, or if somebody's pointing,
• 14:24
  Speaker 1: or if somebody's waving, and the different things a wave
• 14:27
  Speaker 1: can mean, Like there can be like the nice guy point,
• 14:29
  Speaker 1: like hey, nice job, or like the angry point, like
• 14:32
  Speaker 1: what are you doing when you're driving? Certainly in the city,
• 14:35
  Speaker 1: you need to know what those different things mean. That
• 14:38
  Speaker 1: is exactly right, and that is the essence of the
• 14:42
  Speaker 1: problem that is left to solve. And how do you
• 14:45
  Speaker 1: solve it? Practice train in code, figuring out to figure
• 14:52
  Speaker 1: out a way to give the computers as many inputs
• 14:57
  Speaker 1: as possible, teaching it how to make decisions, and very important,
• 15:02
  Speaker 1: making sure that you teach the computer to know what
• 15:05
  Speaker 1: it is it doesn't know, so that when it doesn't
• 15:08
  Speaker 1: know something, it tells us or it shows us. So
• 15:12
  Speaker 1: then we can sit down and say, Okay, that's a problem.
• 15:14
  Speaker 1: How do we get around that? How do we solve
• 15:17
  Speaker 1: for that? That's really interesting. Fundamentally, this is a discussion
• 15:22
  Speaker 1: about risk, right. I mean, what you're saying is Zoo's
• 15:25
  Speaker 1: vehicles can basically drive themselves now, but not safely enough.
• 15:30
  Speaker 1: That's exactly right, And so I mean one question is
• 15:36
  Speaker 1: how safe are they going to have to be? Right?
• 15:38
  Speaker 1: I imagine as good as human drivers is not good enough.
• 15:43
  Speaker 1: This is clearly a super high stakes, literally a life
• 15:46
  Speaker 1: and death question. No system is infinitely safe. How good
• 15:52
  Speaker 1: is good enough? We have to do way, way, way
• 15:56
  Speaker 1: better than humans today, both on the crashes and on
• 16:01
  Speaker 1: the number of miles driven per incident, basically and twice
• 16:08
  Speaker 1: twice as good. That's like, how much how goodes it
• 16:11
  Speaker 1: have to be? Like in a purely rational world, a
• 16:14
  Speaker 1: little bit better would be good enough. Right. Human beings
• 16:16
  Speaker 1: are not just purely irrational. They are very rational, but
• 16:19
  Speaker 1: they are not purely irrational, and so again I don't.
• 16:22
  Speaker 1: None of us in the industry have given our metrics,
• 16:25
  Speaker 1: so I'm not going to be the first one to
• 16:26
  Speaker 1: do that. There's a reason we haven't. But we have
• 16:29
  Speaker 1: to be much safer than humans. This is not a
• 16:32
  Speaker 1: be as safe as the type situation a little bit better.
• 16:34
  Speaker 1: I would not consider that to be a responsible thing
• 16:37
  Speaker 1: to do. In a minute, in the Lightning round, I
• 16:40
  Speaker 1: should tells us where of all the places she's lived,
• 16:43
  Speaker 1: human drivers are the worst. Also one domain where AI
• 16:47
  Speaker 1: will never be better than humans. Okay, let's get back
• 16:55
  Speaker 1: to the show. We're going to close with the Lightning round.
• 16:58
  Speaker 1: So I love this. I love the conversation. I love
• 17:01
  Speaker 1: talking about big, complicated technical things. But I also love
• 17:05
  Speaker 1: asking lots of questions really fast at the end of
• 17:09
  Speaker 1: an interview. Are you ready? I am. What is the
• 17:14
  Speaker 1: one piece of advice you'd give to somebody who is
• 17:16
  Speaker 1: trying to solve a hard problem? Break it down. What's
• 17:20
  Speaker 1: the biggest misconception people have about self driving cars? That
• 17:24
  Speaker 1: cameras only, that cameras are enough? That's the tesla you Yes,
• 17:32
  Speaker 1: what driving advice have you given your sixteen year old
• 17:34
  Speaker 1: daughter who is learning to drive. Relax and pay attention.
• 17:39
  Speaker 1: What is one domain where AI will never be better
• 17:43
  Speaker 1: than humans? And don't say love understanding the soul of
• 17:48
  Speaker 1: a human empathy, empathy. Of all the places you've lived,
• 17:54
  Speaker 1: where were the drivers the worst? You're gonna get me
• 17:57
  Speaker 1: in trouble? Israel was pretty tough driving environment standpoint. I
• 18:02
  Speaker 1: love the country. I would live there again. Driving there
• 18:05
  Speaker 1: is pretty tough. Interesting in terms of like norms and I, Oh,
• 18:09
  Speaker 1: you go, right, it's basically I go, I go pretty much.
• 18:13
  Speaker 1: So where have AI engineers underrated humans self driving? And
• 18:19
  Speaker 1: where have AI engineers overrated humans? What are humans worse at? Oh?
• 18:23
  Speaker 1: We cannot process what I call linear known processing where
• 18:26
  Speaker 1: the rules are clear, the algorithm is clear, we will
• 18:31
  Speaker 1: never beat the machine. Yeah, so we're terrible at chess,
• 18:36
  Speaker 1: but actually pretty good at driving. That's exactly right. Well,
• 18:40
  Speaker 1: this was delightful. Thank you for your time. I really
• 18:43
  Speaker 1: enjoyed it too. Thank you. I have to thank you
• 18:45
  Speaker 1: for something that nobody has done, and I do a
• 18:48
  Speaker 1: lot of these over the years. You pushed me to roots,
• 18:52
  Speaker 1: to the root of and to finding a way to
• 18:56
  Speaker 1: decipher the essence of self driving and why it's hard,
• 18:59
  Speaker 1: and I really appreciate it. I learned something today. Aisha
• 19:04
  Speaker 1: Evans is the CEO of Zoos. Today's show was produced
• 19:08
  Speaker 1: by Edith Russelo. It was edited by Kate Parkinson Morgan
• 19:12
  Speaker 1: and Robert Smith, and it was engineered by Amanda kay Wong.
• 19:15
  Speaker 1: Theme music by Luis Gara. Our development team is Lee,
• 19:17
  Speaker 1: Tom Mulad and Justine Lang. A huge team of people
• 19:20
  Speaker 1: makes What's Your Problem possible. That team includes, but is
• 19:24
  Speaker 1: not limited to, Jacob Weisberg, Na Lobel, Heather Fame, John Schnars,
• 19:28
  Speaker 1: Kerry Brodie, Carli mcgleory, Christina Sullivan, Jason Gambrel, Grant Hayes,
• 19:32
  Speaker 1: Eric Sandler, Maggie Taylor, Morgan Ratner, Nicole Morano, Mary Beth Smith,
• 19:36
  Speaker 1: Royston Breserve, Maya Kanig, Daniella Lakhan, Kazia Tan and David Blefer.
• 19:40
  Speaker 1: What's Your Problem is a co production of Pushkin Industries
• 19:43
  Speaker 1: and iHeartMedia. To find more Pushkin podcast listen on the
• 19:46
  Speaker 1: iHeartRadio app, Apple Podcasts, or where Effort. I'm Jacob Boldstein
• 19:51
  Speaker 1: and I'll be back next week with another episode of
• 19:53
  Speaker 1: What's Your Problem