July 11, 2024 • 42 mins
Jimmy Buffi is the CEO and co-founder of Reboot Motion, which uses biomechanics to help athletes in Major League Baseball and the NBA. Jimmy's problem is this: How do you turn data about how professional athletes move into knowledge that helps them perform better?
This is the second episode of our series about people who are working at the frontiers of technology to help elite athletes perform better.
Music: Let's Have Some Fruit (The Fruit Song) by J Buffi
See omnystudio.com/listener for privacy information.
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Speaker 1 (00:08):
Pushkin.
Speaker 2 (00:16):
Because I didn't know that sports biomechanics could be a career.
I decided to go to grad school and initially start
working on prosthetic limbs. So that was the first two
years of grad school. Then about two years in I
discovered baseball pitching biomechanics research. The funny thing that happened
(00:36):
there was I gave a PhD committee meeting where I
spent most of the time talking about prosthetic limbs, and
then I spent the last few minutes as an aside
on the baseball pitching research I found. And my committee
was like, Jimmy, the last few minutes were way better
than the first forty fives.
Speaker 3 (00:55):
So I was like, all right.
Speaker 2 (00:57):
So then they were like, we'll let you do baseball
pitching biomechanics as your PhD work, but just so you know,
it might be really hard to have a career doing that.
But you know, they were like, if you want to
go for it, you can go for it. And so
I was like, you know what, Sure, I'll go for it.
Speaker 1 (01:19):
I'm Jacob Goldstein, and this is what's your problem. Today
we have the second episode in our series about people
who are working at the frontiers of technology to help
a lead athletes perform better. My guest today is Jimmy Buffy,
and as it happened, the concerns of his grad school
advisors were unfounded. Jimmy has in fact made a career
(01:40):
out of the biomechanics of pitching in baseball and sports
biomechanics more broadly. When he finished grad school, he got
a job with the Los Angeles Dodgers, and he went
on to co found a company called Reboot Motion that
works with teams in Major League Baseball and the NBA.
Jimmy's problem is this, how do you take massive amounts
(02:01):
of data about how professional athletes move and turn all
that data into information that actually helps those athletes perform better.
You end up doing your dissertation research on the on
the biomechanics of pitching, Yes, of baseball, pitching and baseball. Yeah,
and and then you get hired by the Dodgers.
Speaker 3 (02:23):
Yeah.
Speaker 2 (02:23):
Yeah, that was That was awesome because I originally didn't again,
didn't realize that that could be a thing that could happen.
Speaker 1 (02:30):
Well, and it kind of wasn't right, Like, you're kind
of just coming into this field as it's becoming a
field where you can get a job where it's a.
Speaker 3 (02:38):
Field, right exactly. Yeah, there.
Speaker 2 (02:40):
I mean the challenge then was there wasn't a lot
of options for actually even getting the data that you
need to analyze.
Speaker 1 (02:47):
So ten years ago, like what is the state of
play in this sort of nasson field that you're in
helping to create?
Speaker 2 (02:56):
So the field is, I would say, is like sports biomechanic,
and what that is is being able to analyze the
movement of athletes for lots of purposes, help them reduce
injury risk, help them improve performance.
Speaker 1 (03:10):
And to be clear, like folk, sports biomechanics has been
around forever, right, that's what coaches do. They stay out
there and they watch it. Yeah, And so it's kind
of becoming it's becoming more technical, right, the field is
becoming more technical.
Speaker 3 (03:22):
Yeah.
Speaker 2 (03:22):
So the state of the art relied on what is
called marker based motion capture, which is where you literally
put reflective markers like little balls, you stick them all
over somebody's body. Usually the person has to like strip
their clothes off because you want the markers like literally
like on the skin, on the joints, and then you
(03:45):
have these special cameras that track those markers.
Speaker 1 (03:48):
So you've got like a picture in his underwear with
a bunch of little metal balls, takes them and they're like,
just pitch like you always pitch.
Speaker 3 (03:55):
Right, And that's the challenge.
Speaker 2 (03:57):
That's why that wasn't That's why it wasn't very wide
SPA is a thing people did because it was so
hard to collect the data because ultimately, what you would
need is you need the data on how someone is moving.
Speaker 3 (04:08):
You need to track.
Speaker 2 (04:09):
Where their elbow is, where their wrist is, where their
knees are so that you can analyze it. And the
state of the art for tracking it was an awful
experience for the people you were trying to track.
Speaker 1 (04:18):
That presumably would mean they didn't pitch like they usually exactly,
because they don't usually stand there in their underwear with
met Were they really in their underwear by the way,
I'm saying it because it sounds absurd, but is that
actually what they were doing.
Speaker 2 (04:29):
That's actually you strip down to your your boxers, your
boxer briefs, and that's it, that's all you're wearing.
Speaker 1 (04:35):
So it basically didn't work, and it basically wasn't very
widely used as a result.
Speaker 2 (04:39):
Right exactly, Yeah, you yeah, you look at studies in
that field, and people would be throwing like several miles
an hour slower than they would be throwing when they
weren't wearing all that stuff. So what changes computer vision?
That was the big That was the big inflection point. Now,
(05:00):
to be fair, like, even when I was finishing my PhD,
and I'll give them, I'll give them a shout out,
there was a company that was already like working really
hard to solve this problem for baseball teams that I
was getting that I got to be familiar with, called Kinnetrax.
But yeah, the big inflection point was computer vision, basically
(05:21):
using artificial intelligence to identify where those joints are in
a camera image rather than needing to paste those reflective markers.
Speaker 1 (05:32):
So computer vision takes off. You're working at the Dodgers,
and then eventually in twenty nineteen, right, you leave the
Dodgers and you start your company a reboot motion, what
does your company do?
Speaker 2 (05:45):
We do what we call biomechanics as a service, So
we try to analyze this computer vision data at a
very large scale to help teams and coaches make use
of it to help athletes get better. Bas Yeah, that says.
Speaker 1 (06:03):
But bess Yah and and who are your customers?
Speaker 2 (06:06):
Our customers are Major League Baseball teams actually NBA teams,
so we've gotten into basketball also sort of like league
wide data providers. So yeah, leagues teams is basically our
sweet spot.
Speaker 1 (06:24):
So let's talk. Let's talk in like a little more
detail about about what you actually do, right, tell me
the story of what you do.
Speaker 2 (06:33):
So, Evan, my co founder, Evan Demchik, he likes to
call this the biomechanics Trainkay.
Speaker 1 (06:41):
Let's take a ride on the biomechanics trend.
Speaker 2 (06:43):
And we call it that because with the way our
product works is we let people get on the train
at whatever stop works for them, and get off the
train at whatever stop works for them.
Speaker 1 (06:53):
How far are we going to go with this metaphor
of a little o'b nervous about it?
Speaker 3 (06:57):
That might be as far as we go.
Speaker 1 (06:59):
Okay, good, good, So just tell it to me. Start
at whatever seems like the beginning of a you know,
a of an encounter, and so I'd like to understand
how that works. That's really kind of a way to
think about it. So let's start with the data, right,
what is a basic what is the basic thing that's.
Speaker 2 (07:18):
Happening So the very first thing that happens is you
record videos of the athlete doing the athletic motion. So
we'll talk about pitching, So you record videos of a
pitcher pitching. Our product, we actually have implemented our own
computer vision models, so we can do that if people want.
But generally speaking, people have systems like Kinetrax is one
(07:43):
I've mentioned that, Hawkeye is another popular one where there
is a system in place that has the cameras that
record the videos and then runs those computer vision models.
What those computer vision models do is they extract the
locations in three dimensional space of all of like the
joint centers. So where's my elbow, where's my wrist, where's
(08:03):
my knee? In three dimensional space? That's what comes out
of these computer vision systems.
Speaker 1 (08:08):
Okay, so pretty much everybody has that at this point,
Like every professional baseball team has that for every pitch
in every game at this point.
Speaker 3 (08:17):
Yes, exactly.
Speaker 2 (08:18):
Okay, So it's a ton a ton of data. So
that's another challenge that we've solved, is not only how
do you do this, but how do you do this
at a very large scale?
Speaker 1 (08:27):
Okay, so this data, everybody's got it now, and you're not.
You can sort of process the data, but that's not
your special sauce. That's not your secret sauce, right, So
typically they'll send you that that data of like, here's
all the body points. Here is how they're moving in
physical space. Then what do you do with it?
Speaker 2 (08:44):
So, yeah, this is where the special sauce comes in.
So the first step to that is how do you
turn those key points into a human skeleton. So you've
got to figure out, like where do the bones connect,
what sort of degrees of freedom do those bones have,
So then you can figure out how do those key
points animate a human skeleton.
Speaker 1 (09:05):
So you're sort of rebuilding it. It's like you start
with the picture of a person and then you turn
it into a bunch of data points, and now you've
got to kind of build the person back up again from.
Speaker 2 (09:13):
The day exactly exactly. So now you have an actual
human skeleton where the shoulder is rotating, the elbow is flexing,
the knee is flexing, the hips are rotating. And now
once you do that, now you can understand that data
in the context of how the body works. Okay, so
once we've done that, then we calculate how energy flows
(09:34):
through the body, we calculate how momentum flows through the body,
and once we've done that, we can analyze how efficiently
the athlete is moving. Are they generating energy and momentum
in the direction that they want to generate in? What
is that desired direction? So we then we calculate all
sorts of metrics around movement efficiency and direction. Then once
(09:54):
we calculate all those metrics, now we can understand how
those relate to what you're trying to do. Throw the
ball as hard as possible.
Speaker 1 (10:02):
So so presumably with the picture, what you want to
optimize for is is having as much of the picture's
energy of their body go toward making the ball go
toward home plate. Exactly right, I mean that is that? Yeah,
they mail optimization problem mail it.
Speaker 2 (10:17):
Yeah, Yeah, that's exactly it. And that's the problem that
we try to understand. So when we build our sort
of models regarding like how does a pitcher create efficient
fastball velocity, one of the most important things that comes
out of those models is lining up the direction of
your torsore rotation with the direction of your arm rotation.
Speaker 1 (10:34):
The pitching bution is crazy complex, right, Like they're they
kick their leg up and they got their front arms
doing something and their back arms going back like a
lot is happening. Yeah, the sort of platonic ideal is
every little millimeter of every motion is going toward maximizing
the energy of the ball going toward home plate.
Speaker 2 (10:52):
Yes, and not just not just maximizing like in a vacuum,
but doing it in the most efficient way, because if
you just sort of maximize in a vacuum, maybe you're
transferring that energy in a way that hurts your elbow.
You're transferring that energy in a way that hurts your shoulder.
So not only do we figure out how can a
pitcher maximize it, but we try to figure out how
they can have that energy and momentum go in a
(11:14):
direction that doesn't hurt their joints, So try to have
them throw the ball a little harder while also reducing
their injury risk a little bit.
Speaker 1 (11:23):
So you're whatever doing the math at reboot HQ, and
then what are you sending back to the.
Speaker 2 (11:33):
Team, So some teams so it sort of so again,
all right, I told you that was the end of
the biomechanics train analogy.
Speaker 3 (11:41):
I'm going to bring it back for a brief second.
Speaker 1 (11:43):
Okay, I'm ready.
Speaker 2 (11:45):
So we go all the way to building a report
that has a bunch of suggestions. So there's a report
that's like, this is how efficient you are. You can
like tilt your torso a little bit to be a
little bit more efficient. You can tilt your arm a
little bit to be a little bit more efficient. So
we go all the way to generating a report that's
like the final stop on the train.
Speaker 1 (12:04):
And that's a report for for one pitcher.
Speaker 3 (12:06):
Yeah, that's a report on a pitcher for whatever.
Speaker 1 (12:09):
And and in a way that's like the nerdiest it's
what a pitching coach does, but just in a way
nerdier way.
Speaker 3 (12:16):
Yeah.
Speaker 2 (12:16):
Well, so we try to sort of like give the
coaches superpowers, you know, even though that you know, the
coaches like can look at an athlete and understand a
lot about the athlete just by looking at them. We
try to make a report that can really amplify what
the coach is already doing, maybe help them discover some
things they weren't thinking about, or measure some things that
(12:39):
they were thinking about, but now they can track those
a little bit easier. So that's you know, that's the
ultimate thing that we produces a report that can sort
of like we say, give a coach superpowers.
Speaker 1 (12:51):
Where was the trained metaphor doing that? Is there an
earlier station of disembarkation exactly?
Speaker 2 (12:57):
So a lot of teams now are hiring people with
biomechanics and analytics backgrounds, so rather than just use our
reports out of the box, they want to build their
own reports and their own statistical models and their own
AI models. So we also get let people get off
the train a little bit earlier and build whatever they
want on top of the data that we're generating.
Speaker 1 (13:19):
Are they not going to disintermediate you once those people
are there? Does that reduce the value you provide to
the team.
Speaker 2 (13:26):
Now because we still have to process all that data.
Speaker 1 (13:29):
Do you have some like IP or like why can't
somebody like you who works for a team just do
that without you?
Speaker 2 (13:36):
That is a great question. We answered this question all
the time. Is because it's a very complex engineering problem.
Not only to do all the math that the physics
based math, to calculate the energy, calculate the momentum, like
all of that math is really hard, but also to
do it at a very large scale. So someone like
(13:58):
me in grad school learned how to do that on
a sample size. You know, my PhD was actually really
just one pitch, but lots of people do it on
like ten pitches or maybe one hundred pitches, So we
do it on several thousand pitches like and swings like
every morning.
Speaker 3 (14:18):
You know.
Speaker 2 (14:18):
There's just every team has like seven affiliates, so there's
you know, one hundred and fifty games every day that
need to be.
Speaker 1 (14:26):
So you're doing this on farm teams as well.
Speaker 3 (14:28):
Yeah, exactly.
Speaker 2 (14:29):
So not only did we solve the problem of doing
it for like one pitcher in a way that's really actionable,
but we solved the problem doing it for every game
every day, you know, so that you have the data
when you wake up.
Speaker 1 (14:44):
So you guys are doing it at scale. The answer
to why it is that that there is in fact
an economy of scale, a benefit of scale.
Speaker 3 (14:51):
Yes, which you have, Yes, exactly, Yeah. Yeah.
Speaker 1 (14:54):
What's what's a specific example of a thing that a
coach might tell a pitcher in response to your report
to try and get them to throw whatever differently?
Speaker 3 (15:05):
A really.
Speaker 2 (15:08):
Common low hanging fruit type of piece of feedback that
often comes out of the reports is how a pitcher
is using their lead arm in a typical pitching motion,
the pitcher will reach forward with their lead arm.
Speaker 1 (15:24):
So, just to be clear, the lead arm is the
arm that is not holding the ball.
Speaker 3 (15:27):
Right right, yeah, the arm in front of you.
Speaker 1 (15:29):
Yeah.
Speaker 3 (15:29):
Yeah.
Speaker 2 (15:30):
A pitcher will reach forward with that lead arm while
the rear arm is holding the baseball, and they'll rotate
that lead arm really hard, and that's the thing that
kind of initiates the torso rotation. So a very common
flaw that we see is if a pitcher has a
very vertical pitching arm, they're pitching the ball way over
(15:51):
the top of their head, but their lead arm when
they pull it through, when they swing it through, they
swing it in a very flat.
Speaker 1 (15:58):
Plane as horizontal.
Speaker 2 (16:01):
Horizontal, right, yeah, That is not a very efficient plane
to use when you're throwing the ball on a very
vertical plane. So a very common low hang piece of
fruit feedback that comes out of the reports is having
pitchers just try to rotate their lead arm pull with
their lead arm in a more vertical plane to better
(16:21):
match what their torso is doing, a better match with
their pitching arm is doing.
Speaker 1 (16:26):
That's a good one. I feel like that one's so
simple that you don't want it to get out that
everybody ell to start looking at it.
Speaker 2 (16:31):
No, I mean really, I mean like it's this has
happened when I went to talk to a team and
we talked about some pieces, you know, some low hanging fruit,
and they're like, okay, great, we'll take the lead arm thing,
will implement it everywhere. And I'm like, well, what about
like the other ten pages of the report.
Speaker 3 (16:49):
Good with the lead arm thing.
Speaker 1 (16:52):
Thanks by so for you. The end of the train
is the report. But that report goes to the coach, right,
and so presumably the meaningful change hasn't happened yet, right,
It has to somehow get from the coach to the picture.
And like, I know that piece of it is not
your business now, but it was kind of your business
when you were at the Dodgers. Presumably you're familiar with
(17:14):
it now, Like, how does that piece of it work?
Is it like the pitching coach is like reading from
the report to the picture. I imagine not, but I
don't know.
Speaker 2 (17:20):
No, definitely, definite, definitely not. Even at the Dodgers, my
role was not being the one to coach the players.
Speaker 1 (17:32):
It's like, whatever you do, don't talk to the pictures. Man,
go back to your computer.
Speaker 2 (17:36):
Yeah no, no, I mean thankfully I got to be
in the in the room as you know, dark Walld,
the interaction is happening. But I think that is the
the art of coaching that is so important is understanding
the picture and how the pitcher thinks about themselves and
giving the right feedback to have the picture do the
(18:00):
thing that you that you want them to do.
Speaker 1 (18:02):
Uh huh. Knowing how to talk to a player in
a way that is not generic. Presumably different pitchers need
to hear different things, even if the outcome is the same, right.
Speaker 2 (18:12):
I mean, there's a there's a classic like debate in
baseball of like do you swing down on the ball
or do you swing with an uppercut? And in reality,
like the batpath is an arc, the path goes down
and then the path goes up. But some coach, some
players respond better when a coach will say swing down
on the ball, and some players spawn better when a
(18:35):
coach will say, you know, have get a little bit
more uppercut, do your swing. But in reality, you know,
the bat goes down and the bat goes up. So
it's like really understanding what is the player what helps
the player the most?
Speaker 1 (18:45):
So I heard you use this phrase in another interview
that I think is kind of what you're talking about here,
And it's feel versus real? What is that? What is
feel versus real?
Speaker 2 (18:55):
So it's exactly what we're talking about. Is sometimes with
the apt let feels like they're doing is not.
Speaker 3 (19:03):
What's actually happening.
Speaker 2 (19:05):
But if you understand what the athlete feels like they're doing,
you can give feedback that interacts with how they're feeling.
So if they feel like they're swinging down on the
ball and you give them feedback related to that, even
if they're actually swinging with an uppercut, you know, the
important thing is like how do they feel and how
do you give them feedback related to how they feel,
(19:26):
which then impacts is real. But it's understanding the interplay
between the feel and the real.
Speaker 1 (19:32):
Yeah, it's wild that, like there is there is a
human being doing a thing, and then there's this huge
industrial machinery of your company and the team and all
of these scientists and all these cameras and computers that
are trying to get this human being to change their
behavior in a very subtle way.
Speaker 3 (19:52):
Yeah, exactly.
Speaker 1 (19:53):
It's a behavior that is in many ways intuitive right,
it's sort of partly conscious but partly intuitive him like
there's a really interesting human being at the center.
Speaker 3 (20:05):
Of all of this.
Speaker 2 (20:06):
Yeah, And I think that's also why it's so important
to have the coach in the loop, because they understand
the human being even beyond just like the feel versus
real aspect of like did the athlete not get a
good night's sleep last night, then maybe today is not
a good day to give them feedback. Are they going
through challenges, you know, with a significant other, are they
(20:27):
going through challenges in other ways? Or today are they
really fired up? So today is a really good day
to give them feedback. It's like understanding the human being.
I'll give him a shout out. Connor McGuinness is the
assistant pitching coach right now for the Dodgers, and he
was so good at this. He would always talk about
he never felt comfortable truly coaching a player until the
(20:49):
player trusted him, until he felt like he had a
good enough relationship with the player with the player would
feel comfortable taking his feedback.
Speaker 1 (20:57):
Like start with the player as a human beings, Start
with the player and get to get to.
Speaker 2 (21:02):
And this is why I think it's going to be
really really difficult to have a product that goes direct
to a player. We've dabbled with that, you know, and
lots of companies have dabbled with film yourself with your
iPhone and you get some feedback, you know, on your movement.
But I think there's so much subjective stuff that goes
(21:23):
into what we're talking about, how does the athlete move
and how do they feel like they're moving, that I
think it's going to be really hard to solve the
challenge of giving an athlete feedback without a coach.
Speaker 1 (21:36):
In a minute, Jimmy's work in the NBA and why
figuring out how to help NBA players shoot better is
actually a really hard problem. What are you doing in basketball?
Speaker 2 (21:55):
Basketball is very very cool because it's a slightly different
channe In baseball, like we've been talking about, the challenge
for a pitcher is mostly just maximizing efficiency, or even
for a hitter, you know, they're reacting to the pitcher,
but they're still trying to swing as hard as they
can and hit the ball as far as they can.
(22:18):
So basketball is very different because you got a target.
You're not trying to do this thing as hard as
humanly possible.
Speaker 1 (22:25):
The target is the hoop. The targets to be clear, the.
Speaker 3 (22:28):
Target is the hoop.
Speaker 2 (22:29):
So that's a really interesting kind of like motor control
problem of no matter where you are on the court,
how good are you at getting the ball to do
what you want it to do. We've been finding that
there seems to be lots of trade offs that good
(22:49):
shooters are making regarding like when do they release the
ball in the course of their jump, how high of
an arc do they use when they release the ball,
how high they have their release point when they.
Speaker 3 (23:01):
Release the ball.
Speaker 2 (23:02):
So there's all sorts of trade offs that these shooters
seem to be making related to how good they are
at controlling their own jump, controlling their own velocity, where
they are on the court, how close the nearest defender is.
It's it's a very different problem.
Speaker 1 (23:18):
Sounds way harder, sounds way way harder, is that right
for you? Harder for you to sort of solve to
write a report that says, do this different thing and
you'll hit a higher percentage of your shots.
Speaker 2 (23:29):
Right exactly? Yeah, And which makes it which makes it fun.
I love solving hard podcasts.
Speaker 1 (23:35):
What have you solved in basketball so far?
Speaker 2 (23:38):
The big the first challenge that we had to solve
was the scale challenge in basketball. There isn't quite as
much there aren't quite as many games in basketball, but
the data is a lot harder to parse because the
events aren't as distinct. It's not like it's not like
this is a shot, I mean only for free throws.
Speaker 1 (23:59):
It's a more continuous.
Speaker 2 (24:00):
Continuous motion. So the first big challenge was how do
we even just isolate the events that we care about.
Speaker 1 (24:06):
Like what is time? When does a shot begin? When
does a time equals zero for shot?
Speaker 2 (24:11):
But kind of debatable, right exactly. So that, yeah, that
was the first big challenge that we had to solve.
Was just sort of like the data engineering challenge. And now,
like I said, our reports are more than telling you,
you know, how to be more or less efficient. It's
trying to surface the trade offs that you're making. Where
(24:32):
in your jump are you are you releasing the ball,
how high is your release point? What kind of arc
are you using? And how does that compare to other
arcs you could be using?
Speaker 1 (24:41):
What like what what are the trade offs?
Speaker 2 (24:44):
A really really interesting trade off to me is how
much arc are you putting on the basketball? Not just
to like evade a defender. But there's a trade off
where if you shoot the ball at a highhigher arc,
you have to use more velocity to get the ball
to go all the way to the rim.
Speaker 1 (25:07):
Right, because it's going to travel farther in total in space.
Speaker 2 (25:10):
Right, And if you are not the most coordinated human,
it might be harder for you to add more velocity
in a really in a really precise way. So the
more arc you have, the more prone you can be
to what we would call like velocity errors overshooting undershooting.
The advantage you get when you create more arc is
(25:33):
if you if you imagine the ball coming down from
that arc and the angle the angle with which it
approaches the rim, it approaches at a steeper angle, which
means you literally have more rim to aim at.
Speaker 3 (25:44):
So if you're hot, so if you shoot.
Speaker 2 (25:46):
Higher, you know this is a steph Curry thing. He
has a really high arc. Presumably this is the hypothesis,
because he's one of the most coordinated humans on the.
Speaker 1 (25:55):
Planet, so he sea.
Speaker 2 (25:59):
So he can use a really high arc because he's
really good at controlling his velocity output. Oh huh, so
he can really dial in how hard he releases the ball,
which means he gets the advantage of having more rimmed
to aim at, where as somebody who's bad at controlling
their velocity output when they try to aim higher, they'll
just overshoot an undershoot.
Speaker 1 (26:17):
So is the notion, and this is something of an oversimplification,
but that for any given level of coordination, there is
some optimal arc, and the more coordinated you are, the
higher the optimal arc would be for you setting aside defense.
Speaker 3 (26:33):
Maybe that's the hypothesis.
Speaker 1 (26:35):
Yeah, I mean that seems like where what you were
saying goes exactly.
Speaker 2 (26:40):
Yeah, that's the hypothesis. So that's what we're trying to
look into.
Speaker 1 (26:43):
Okay, I'll be curious to see what you figure out.
Are free throws easier? Did you think of starting with
free throws?
Speaker 3 (26:51):
Yeah?
Speaker 2 (26:52):
Right, right now. Honestly, the phase we're at in basketball
is mostly just collecting a lot of data. So you know,
a starting pitcher will you know, throw ninety pitches in
a game, and now you have a sample size of
ninety pitches that are all the same, whereas a basketball
shooter only has a couple of free throws in a game.
You know, we're working on ways with teams of collecting
(27:15):
data in a practice setting, so getting a lot of
this data in a bigger chunks. But really at this
point it's collecting a lot of data so we can
do some of this research to explore some of these hypotheses.
Speaker 1 (27:27):
Huh. So it seems like in basketball you're where you
were ten years ago or something in.
Speaker 3 (27:33):
Baseball, right exactly.
Speaker 1 (27:35):
So basketball is sort of one kind of frontier. It
seems like one thing you're trying to figure out and
haven't really cracked yet. What are some of the other
frontiers the other things you're figuring out, whether it's in
baseball or in the fundamental technology or whatever. What are
you working on?
Speaker 2 (27:54):
We want to try to have a computer vision be
even more accessible. You know, there's been a lot and
a lot, a lot a lot of improvements over the
last ten years in computer vision where you can do
really good motion capture with just your iPhone, but still
(28:17):
for certain specialized movements, pitching, shooting, things like that, there's
still have little ways to go to get really really
good data straight from your iPhone. So that's one of
the frontiers, is like continuing to try to help understand
how to make computer vision more accessible. Another one is
(28:40):
more fitness based analysis. You know, it's interesting to think
about companies like Mirror and companies that have tried to
give people feedback and like a fitness environment, But how
do you give someone or how do you give like
a strength and conditioning coach good feedback that can be
(29:00):
used in a weight room setting. Yeah, and then continue
to explore other emotions and other sports, Like football is
a really interesting one because a lot of football is
interacting with other humans. Indeed, yeah, I mean that's obvious,
but like, how do you get a takeaway from like
(29:21):
two linemen interacting?
Speaker 1 (29:24):
Ye, things, but that one I wonder. I mean, it
seems like if you think of the line, you know,
in football, it's so they're so on top of each other,
the defensive line, of the defensive line, that I feel
like vision might not be what you want. You might
want sensors, right, you might want pressure sensors in the
lineman's clothes or something. I don't know, I'm just making
that up, but like it seems like that might be
(29:45):
more useful, just because it's hard to see what's going
on in the line.
Speaker 3 (29:47):
Yeah.
Speaker 2 (29:48):
Yeah, yeah, except professional athletes don't like wearing random.
Speaker 1 (29:52):
Things, well are aren't people trying to make sensors like
woven into the clothes. I mean, I feel like there
are ways you would just be putting on your jersey
or putting on your paths or whatever and they would
have the sensors built in.
Speaker 3 (30:05):
Yeah. Yeah, one hundred percent.
Speaker 2 (30:06):
There's lots of really cool technology of that is you know,
you know, microscopic sensors that are just woven, woven into
clothing for sure.
Speaker 1 (30:16):
So so let's talk for a second more about the
consumer side. You sort of touched on it and moved on.
I mean, is that are you actively working on that
or is that just like yeah, it kind of seems interesting,
but not for now. We're too busy, like what's what's
happening on the consumer side.
Speaker 2 (30:33):
We're not actively tackling in the consumer side right now.
And that the reason why we started with professional sports
is one it's because like it's what I know, you know,
I work for the Dodgers, but also because the value
proposition of what we're doing is so impactful. You know, yeah,
you know, you understand, you try to understand, like the
(30:54):
relationship between people have tried to put numbers on this,
it's the people have estimated, it's in the millions of dollars.
But the value of adding one mile an hour of
fastball velocity to a picture, you know, people have valued that,
We have valued that in millions of dollars.
Speaker 1 (31:10):
Well, sure you will tell you millions of dollars, But
what is the like, I don't know what's a what's
a what's a top picture make? These days? I don't
even know anymore.
Speaker 3 (31:20):
I mean, you want to talk about show.
Speaker 1 (31:23):
Half a billion, hundreds of millions, half a billion? Yeah,
so so right, so so the marginal benefit has a
very large value. Yah a million dollars against one hundred
million dollars, like one percent better. If they're making a
hundred million dollars, it's worth a million dollars presumably.
Speaker 2 (31:40):
Yeah, And we start to get the pro sports teams
to believe.
Speaker 1 (31:43):
That, well, how many how many pro sports teams are
paying you at this point, about uh.
Speaker 2 (31:51):
Close to ten in Major League Baseball and a couple
in the NBA.
Speaker 3 (31:55):
The NBA is a lot newer.
Speaker 1 (31:57):
And how big is the field? Like, what's sort of
the state of play in the field of I don't
even know what to say. Biomechanics as a service seems
like a niche construction of it. But what would you
say sports analytics? I mean, I guess that's not quite right.
What how do you construct the broader field?
Speaker 2 (32:15):
Sports analytics is definitely a part of it. The data
that we provide is novel or is different than like
traditional sports analytics. So we don't really have a lot
of companies as competitors. Honestly, our biggest competitors are teams
(32:38):
wanting to try to do this type of thing internally.
How you know, hire a bunch of data engineers, hire
a bunch of software engineers, hire people with biomechanics backgrounds,
and try to build out these pipeline processing pipelines themselves.
Speaker 1 (32:50):
Does every team have like a somebody with a PhD
in biomechanics working for them now?
Speaker 3 (32:55):
In baseball? Yeah?
Speaker 1 (32:57):
Wow?
Speaker 2 (32:58):
In basketball and not Yeah, but they're starting to.
Speaker 1 (33:02):
So I know people, I mean, I think in general
baseball fans like to complain, but so one of the
things they've complained about lately is the way analytics more
broadly made the game more boring, right, like the shift
and changing pictures more frequently and whatever else people complain about.
Are you do you fit into that at all? Uh?
Speaker 3 (33:28):
That's a good that's a good question. Some people.
Speaker 2 (33:35):
Some people complain about how hard pictures are throwing these
days because it creates more strikeouts, and people think strikeouts
are boring.
Speaker 3 (33:45):
So maybe, yeah, so.
Speaker 1 (33:47):
Maybe you need to get better at helping hitters. Really
you're out that way, you can even at back up, all.
Speaker 2 (33:53):
Right, And that's what we talked about takeaways four Hitters
are harder because they're reacting to the picture.
Speaker 1 (33:59):
So if you think about the field, what your company
say in five years, yeah, whatever is your kind of
medium term future that you think about, what is the
company in the sort of the world, the sports world
that you're interacting with look like at that time and
say whatever, five years, ten years.
Speaker 2 (34:18):
What I hope is that what we are trying to
foster is an environment where coaches have really incredible tools
at their disposal to understand how an athlete moves. So,
you know, we talk about the very beginning where sort
of the still more or less the state of the
(34:40):
art is a coach just looks at an athlete, watches
video of an athlete, and tries to give the athlete
feedback regarding what they see on the video, what they
see with their eyes. We hope that the standard becomes
you use an analytical tool to help you understand how
the athlete is moving and to really like level up
(35:02):
your coaching because now you have this objective information about
how the athlete is moving. I kind of I kind
of make the analogy related to just radar guns. Before
radar guns were a thing, a coach would just like
look at a picture and be like, oh, that looks
pretty fast, you know, make an adjustment, and I think
that looks a little faster. But then radar guns came out,
(35:27):
and you could actually measure how fast the picture was throwing,
and you could actually measure if the picture is getting
throwing the ball harder based on your feedback.
Speaker 1 (35:35):
Yeah, and now you're you're doing that but in a
in a way more complex way.
Speaker 3 (35:41):
Exactly.
Speaker 1 (35:42):
Yeah, we'll be back in a minute with the lightning round.
Let's do the lightning rounds. Let's start with a few
(36:03):
baseball questions. Who's the most underrated picture of all time?
Speaker 2 (36:08):
Whoa underrated picture of all time? Oh my goodness, I
don't know if I can give you one that's like
all time, because I don't know if that's fair. I'm
sure I'm not thinking of everybody of.
Speaker 1 (36:24):
Your lifetime, of your lifetime.
Speaker 3 (36:26):
I grew up a hardcore Red Sox fan.
Speaker 2 (36:29):
I grew up in Rhode Island, and the first one
that comes to mind mostly in the Red Sox atmosphere,
but I wonder if you could make a broader argument
was Tim Wakefield, who was a knuckleball pitcher for the
Red Sox and what made amazing physics amazing physics and aerodynamics,
And the reason being is he just did so many
(36:53):
things for the Red Sox, ate up so many innings
and was so effective closing, starting, whatever, But he never
got incredible recognition because it was a knuckleball that was going,
you know, fifty five sixty miles an hour.
Speaker 1 (37:07):
What's one thing you would change about baseball to make
it more popular?
Speaker 2 (37:13):
I do feel like actually the changes that are being
made are good ones, in like reducing the amount of downtime.
Speaker 1 (37:23):
A pitch clock, it's one, is that the way you're
thinking of?
Speaker 2 (37:26):
Or yeah, yeah, yeah, exactly, yeah, a pitch clock. The
thing that's challenging for me as a biomechanist is when
you reduced the amount of time that a pitcher has
to throw, you theoretically could introduce more fatigue, which theoretically
also introduces more injury risk. So this is something that
we've been thinking about. Is like, So for me, while
(37:46):
I like that change that baseball is making to make
the game, to speed the game up, I think the
pitchers also need to train a little bit differently. Oh,
that's to be able to better withstand the shorter rest time.
Speaker 1 (38:03):
Are there aspects of your work and the changes you've
seen over the course of your career that illuminate sort
of broader changes in computer vision and AI more generally.
Speaker 2 (38:16):
Yeah, In particular, the most important one has been the
improvement in computer vision, which because computer vision at its
core is artificial and intelligence neural networks, and as those
as that that technology has gotten better and better, you know,
the latest and greatest people always talk about like the
Transformer model really changed AI. I mean that changed computer
(38:38):
vision too, Like lots of the modern more modern like
computer vision models are based on transformers.
Speaker 1 (38:44):
And which, to be clear to the Transformer model is
what gives us chat GPT, right, The T in GPT
is transformed, right, So how has it affected the computer vision.
Speaker 2 (38:53):
Side making the models more accurate and more efficient? It
used to be you know, a couple of years ago
when I try to run a computer vision model on
my laptop, like it could take an hour just to
like analyze one pitch, one video, and now it takes
a matter of seconds.
Speaker 1 (39:12):
And so what is the what is the bigger implication
of that? Beyond your beyond your work?
Speaker 2 (39:19):
More and more data is available regarding how people move,
you know, like when when I first started, it was
really hard to have data in a baseball game. Now
every major league game, every minor league game, every NBA game,
maybe every G League game, every w NBA game, you know,
every single uh basketball and baseball game, you know, more
(39:44):
or less is now like being recorded with computer vision
to get the three dimensional data about how people are moving.
Just lots and lots of data on how people move.
And this is really impacting. I think lots of fields.
In particular, I think like self driving cars, robots that
are meant to like interact with the world, all rely
(40:05):
on computer vision models. I mean, I think one of
the coolest things about how cars do this sort of
thing is not only do they have to understand where
a person is now, but they're really cool models that
they take where a person is now and the last
like ten seconds of what that person did and try
(40:28):
to predict all the different things that the person might do.
They might run across the street, they might jump out
of the way, they might jump forward, you know, they
might run and chase a soccer ball.
Speaker 1 (40:38):
I mean, my sense is all of the hard edge
cases in self driving cars. Basically, the reason we don't
truly have self driving cars yet is because people are
so hard to understate. Yeah, right, Like if the world
was all self driving cars, then it would be a
solved problem, right, Like the machine could understand what other
machines are going to do. But people, human drivers, human
(41:00):
pedestrians are strange and very hard for machines to understand.
Speaker 3 (41:06):
Yeah.
Speaker 1 (41:07):
Yeah, it's like they need a coach. It's like the
coaching problem again. We found your SoundCloud. Oh yeah, so,
Jimmy Buffett fans are called parrot heads. What are Jimmy
Buffy fans called?
Speaker 3 (41:26):
I never thought about it.
Speaker 1 (41:31):
You have a song called Let's have some Fruit parentheses
the fruit song is fruit a metaphor.
Speaker 3 (41:41):
Leave it up to your imagination. Fair.
Speaker 1 (41:45):
Jimmy Buffy is the co founder and CEO of Reboot
Motion Swanson swe Today's show was produced by Gabriel Hunter Cheng.
(42:06):
It was edited by Lyddy Jean Kott and engineered by
Sarah Bruguer. You can email us at problem at Pushkin
dot Fm. I'm Jacob Goldstein and we'll be back next
week with another episode of What's Your Problems
Pushkin.
Speaker 2 (00:16):
Because I didn't know that sports biomechanics could be a career.
I decided to go to grad school and initially start
working on prosthetic limbs. So that was the first two
years of grad school. Then about two years in I
discovered baseball pitching biomechanics research. The funny thing that happened
(00:36):
there was I gave a PhD committee meeting where I
spent most of the time talking about prosthetic limbs, and
then I spent the last few minutes as an aside
on the baseball pitching research I found. And my committee
was like, Jimmy, the last few minutes were way better
than the first forty fives.
Speaker 3 (00:55):
So I was like, all right.
Speaker 2 (00:57):
So then they were like, we'll let you do baseball
pitching biomechanics as your PhD work, but just so you know,
it might be really hard to have a career doing that.
But you know, they were like, if you want to
go for it, you can go for it. And so
I was like, you know what, Sure, I'll go for it.
Speaker 1 (01:19):
I'm Jacob Goldstein, and this is what's your problem. Today
we have the second episode in our series about people
who are working at the frontiers of technology to help
a lead athletes perform better. My guest today is Jimmy Buffy,
and as it happened, the concerns of his grad school
advisors were unfounded. Jimmy has in fact made a career
(01:40):
out of the biomechanics of pitching in baseball and sports
biomechanics more broadly. When he finished grad school, he got
a job with the Los Angeles Dodgers, and he went
on to co found a company called Reboot Motion that
works with teams in Major League Baseball and the NBA.
Jimmy's problem is this, how do you take massive amounts
(02:01):
of data about how professional athletes move and turn all
that data into information that actually helps those athletes perform better.
You end up doing your dissertation research on the on
the biomechanics of pitching, Yes, of baseball, pitching and baseball. Yeah,
and and then you get hired by the Dodgers.
Speaker 3 (02:23):
Yeah.
Speaker 2 (02:23):
Yeah, that was That was awesome because I originally didn't again,
didn't realize that that could be a thing that could happen.
Speaker 1 (02:30):
Well, and it kind of wasn't right, Like, you're kind
of just coming into this field as it's becoming a
field where you can get a job where it's a.
Speaker 3 (02:38):
Field, right exactly. Yeah, there.
Speaker 2 (02:40):
I mean the challenge then was there wasn't a lot
of options for actually even getting the data that you
need to analyze.
Speaker 1 (02:47):
So ten years ago, like what is the state of
play in this sort of nasson field that you're in
helping to create?
Speaker 2 (02:56):
So the field is, I would say, is like sports biomechanic,
and what that is is being able to analyze the
movement of athletes for lots of purposes, help them reduce
injury risk, help them improve performance.
Speaker 1 (03:10):
And to be clear, like folk, sports biomechanics has been
around forever, right, that's what coaches do. They stay out
there and they watch it. Yeah, And so it's kind
of becoming it's becoming more technical, right, the field is
becoming more technical.
Speaker 3 (03:22):
Yeah.
Speaker 2 (03:22):
So the state of the art relied on what is
called marker based motion capture, which is where you literally
put reflective markers like little balls, you stick them all
over somebody's body. Usually the person has to like strip
their clothes off because you want the markers like literally
like on the skin, on the joints, and then you
(03:45):
have these special cameras that track those markers.
Speaker 1 (03:48):
So you've got like a picture in his underwear with
a bunch of little metal balls, takes them and they're like,
just pitch like you always pitch.
Speaker 3 (03:55):
Right, And that's the challenge.
Speaker 2 (03:57):
That's why that wasn't That's why it wasn't very wide
SPA is a thing people did because it was so
hard to collect the data because ultimately, what you would
need is you need the data on how someone is moving.
Speaker 3 (04:08):
You need to track.
Speaker 2 (04:09):
Where their elbow is, where their wrist is, where their
knees are so that you can analyze it. And the
state of the art for tracking it was an awful
experience for the people you were trying to track.
Speaker 1 (04:18):
That presumably would mean they didn't pitch like they usually exactly,
because they don't usually stand there in their underwear with
met Were they really in their underwear by the way,
I'm saying it because it sounds absurd, but is that
actually what they were doing.
Speaker 2 (04:29):
That's actually you strip down to your your boxers, your
boxer briefs, and that's it, that's all you're wearing.
Speaker 1 (04:35):
So it basically didn't work, and it basically wasn't very
widely used as a result.
Speaker 2 (04:39):
Right exactly, Yeah, you yeah, you look at studies in
that field, and people would be throwing like several miles
an hour slower than they would be throwing when they
weren't wearing all that stuff. So what changes computer vision?
That was the big That was the big inflection point. Now,
(05:00):
to be fair, like, even when I was finishing my PhD,
and I'll give them, I'll give them a shout out,
there was a company that was already like working really
hard to solve this problem for baseball teams that I
was getting that I got to be familiar with, called Kinnetrax.
But yeah, the big inflection point was computer vision, basically
(05:21):
using artificial intelligence to identify where those joints are in
a camera image rather than needing to paste those reflective markers.
Speaker 1 (05:32):
So computer vision takes off. You're working at the Dodgers,
and then eventually in twenty nineteen, right, you leave the
Dodgers and you start your company a reboot motion, what
does your company do?
Speaker 2 (05:45):
We do what we call biomechanics as a service, So
we try to analyze this computer vision data at a
very large scale to help teams and coaches make use
of it to help athletes get better. Bas Yeah, that says.
Speaker 1 (06:03):
But bess Yah and and who are your customers?
Speaker 2 (06:06):
Our customers are Major League Baseball teams actually NBA teams,
so we've gotten into basketball also sort of like league
wide data providers. So yeah, leagues teams is basically our
sweet spot.
Speaker 1 (06:24):
So let's talk. Let's talk in like a little more
detail about about what you actually do, right, tell me
the story of what you do.
Speaker 2 (06:33):
So, Evan, my co founder, Evan Demchik, he likes to
call this the biomechanics Trainkay.
Speaker 1 (06:41):
Let's take a ride on the biomechanics trend.
Speaker 2 (06:43):
And we call it that because with the way our
product works is we let people get on the train
at whatever stop works for them, and get off the
train at whatever stop works for them.
Speaker 1 (06:53):
How far are we going to go with this metaphor
of a little o'b nervous about it?
Speaker 3 (06:57):
That might be as far as we go.
Speaker 1 (06:59):
Okay, good, good, So just tell it to me. Start
at whatever seems like the beginning of a you know,
a of an encounter, and so I'd like to understand
how that works. That's really kind of a way to
think about it. So let's start with the data, right,
what is a basic what is the basic thing that's.
Speaker 2 (07:18):
Happening So the very first thing that happens is you
record videos of the athlete doing the athletic motion. So
we'll talk about pitching, So you record videos of a
pitcher pitching. Our product, we actually have implemented our own
computer vision models, so we can do that if people want.
But generally speaking, people have systems like Kinetrax is one
(07:43):
I've mentioned that, Hawkeye is another popular one where there
is a system in place that has the cameras that
record the videos and then runs those computer vision models.
What those computer vision models do is they extract the
locations in three dimensional space of all of like the
joint centers. So where's my elbow, where's my wrist, where's
(08:03):
my knee? In three dimensional space? That's what comes out
of these computer vision systems.
Speaker 1 (08:08):
Okay, so pretty much everybody has that at this point,
Like every professional baseball team has that for every pitch
in every game at this point.
Speaker 3 (08:17):
Yes, exactly.
Speaker 2 (08:18):
Okay, So it's a ton a ton of data. So
that's another challenge that we've solved, is not only how
do you do this, but how do you do this
at a very large scale?
Speaker 1 (08:27):
Okay, so this data, everybody's got it now, and you're not.
You can sort of process the data, but that's not
your special sauce. That's not your secret sauce, right, So
typically they'll send you that that data of like, here's
all the body points. Here is how they're moving in
physical space. Then what do you do with it?
Speaker 2 (08:44):
So, yeah, this is where the special sauce comes in.
So the first step to that is how do you
turn those key points into a human skeleton. So you've
got to figure out, like where do the bones connect,
what sort of degrees of freedom do those bones have,
So then you can figure out how do those key
points animate a human skeleton.
Speaker 1 (09:05):
So you're sort of rebuilding it. It's like you start
with the picture of a person and then you turn
it into a bunch of data points, and now you've
got to kind of build the person back up again from.
Speaker 2 (09:13):
The day exactly exactly. So now you have an actual
human skeleton where the shoulder is rotating, the elbow is flexing,
the knee is flexing, the hips are rotating. And now
once you do that, now you can understand that data
in the context of how the body works. Okay, so
once we've done that, then we calculate how energy flows
(09:34):
through the body, we calculate how momentum flows through the body,
and once we've done that, we can analyze how efficiently
the athlete is moving. Are they generating energy and momentum
in the direction that they want to generate in? What
is that desired direction? So we then we calculate all
sorts of metrics around movement efficiency and direction. Then once
(09:54):
we calculate all those metrics, now we can understand how
those relate to what you're trying to do. Throw the
ball as hard as possible.
Speaker 1 (10:02):
So so presumably with the picture, what you want to
optimize for is is having as much of the picture's
energy of their body go toward making the ball go
toward home plate. Exactly right, I mean that is that? Yeah,
they mail optimization problem mail it.
Speaker 2 (10:17):
Yeah, Yeah, that's exactly it. And that's the problem that
we try to understand. So when we build our sort
of models regarding like how does a pitcher create efficient
fastball velocity, one of the most important things that comes
out of those models is lining up the direction of
your torsore rotation with the direction of your arm rotation.
Speaker 1 (10:34):
The pitching bution is crazy complex, right, Like they're they
kick their leg up and they got their front arms
doing something and their back arms going back like a
lot is happening. Yeah, the sort of platonic ideal is
every little millimeter of every motion is going toward maximizing
the energy of the ball going toward home plate.
Speaker 2 (10:52):
Yes, and not just not just maximizing like in a vacuum,
but doing it in the most efficient way, because if
you just sort of maximize in a vacuum, maybe you're
transferring that energy in a way that hurts your elbow.
You're transferring that energy in a way that hurts your shoulder.
So not only do we figure out how can a
pitcher maximize it, but we try to figure out how
they can have that energy and momentum go in a
(11:14):
direction that doesn't hurt their joints, So try to have
them throw the ball a little harder while also reducing
their injury risk a little bit.
Speaker 1 (11:23):
So you're whatever doing the math at reboot HQ, and
then what are you sending back to the.
Speaker 2 (11:33):
Team, So some teams so it sort of so again,
all right, I told you that was the end of
the biomechanics train analogy.
Speaker 3 (11:41):
I'm going to bring it back for a brief second.
Speaker 1 (11:43):
Okay, I'm ready.
Speaker 2 (11:45):
So we go all the way to building a report
that has a bunch of suggestions. So there's a report
that's like, this is how efficient you are. You can
like tilt your torso a little bit to be a
little bit more efficient. You can tilt your arm a
little bit to be a little bit more efficient. So
we go all the way to generating a report that's
like the final stop on the train.
Speaker 1 (12:04):
And that's a report for for one pitcher.
Speaker 3 (12:06):
Yeah, that's a report on a pitcher for whatever.
Speaker 1 (12:09):
And and in a way that's like the nerdiest it's
what a pitching coach does, but just in a way
nerdier way.
Speaker 3 (12:16):
Yeah.
Speaker 2 (12:16):
Well, so we try to sort of like give the
coaches superpowers, you know, even though that you know, the
coaches like can look at an athlete and understand a
lot about the athlete just by looking at them. We
try to make a report that can really amplify what
the coach is already doing, maybe help them discover some
things they weren't thinking about, or measure some things that
(12:39):
they were thinking about, but now they can track those
a little bit easier. So that's you know, that's the
ultimate thing that we produces a report that can sort
of like we say, give a coach superpowers.
Speaker 1 (12:51):
Where was the trained metaphor doing that? Is there an
earlier station of disembarkation exactly?
Speaker 2 (12:57):
So a lot of teams now are hiring people with
biomechanics and analytics backgrounds, so rather than just use our
reports out of the box, they want to build their
own reports and their own statistical models and their own
AI models. So we also get let people get off
the train a little bit earlier and build whatever they
want on top of the data that we're generating.
Speaker 1 (13:19):
Are they not going to disintermediate you once those people
are there? Does that reduce the value you provide to
the team.
Speaker 2 (13:26):
Now because we still have to process all that data.
Speaker 1 (13:29):
Do you have some like IP or like why can't
somebody like you who works for a team just do
that without you?
Speaker 2 (13:36):
That is a great question. We answered this question all
the time. Is because it's a very complex engineering problem.
Not only to do all the math that the physics
based math, to calculate the energy, calculate the momentum, like
all of that math is really hard, but also to
do it at a very large scale. So someone like
(13:58):
me in grad school learned how to do that on
a sample size. You know, my PhD was actually really
just one pitch, but lots of people do it on
like ten pitches or maybe one hundred pitches, So we
do it on several thousand pitches like and swings like
every morning.
Speaker 3 (14:18):
You know.
Speaker 2 (14:18):
There's just every team has like seven affiliates, so there's
you know, one hundred and fifty games every day that
need to be.
Speaker 1 (14:26):
So you're doing this on farm teams as well.
Speaker 3 (14:28):
Yeah, exactly.
Speaker 2 (14:29):
So not only did we solve the problem of doing
it for like one pitcher in a way that's really actionable,
but we solved the problem doing it for every game
every day, you know, so that you have the data
when you wake up.
Speaker 1 (14:44):
So you guys are doing it at scale. The answer
to why it is that that there is in fact
an economy of scale, a benefit of scale.
Speaker 3 (14:51):
Yes, which you have, Yes, exactly, Yeah. Yeah.
Speaker 1 (14:54):
What's what's a specific example of a thing that a
coach might tell a pitcher in response to your report
to try and get them to throw whatever differently?
Speaker 3 (15:05):
A really.
Speaker 2 (15:08):
Common low hanging fruit type of piece of feedback that
often comes out of the reports is how a pitcher
is using their lead arm in a typical pitching motion,
the pitcher will reach forward with their lead arm.
Speaker 1 (15:24):
So, just to be clear, the lead arm is the
arm that is not holding the ball.
Speaker 3 (15:27):
Right right, yeah, the arm in front of you.
Speaker 1 (15:29):
Yeah.
Speaker 3 (15:29):
Yeah.
Speaker 2 (15:30):
A pitcher will reach forward with that lead arm while
the rear arm is holding the baseball, and they'll rotate
that lead arm really hard, and that's the thing that
kind of initiates the torso rotation. So a very common
flaw that we see is if a pitcher has a
very vertical pitching arm, they're pitching the ball way over
(15:51):
the top of their head, but their lead arm when
they pull it through, when they swing it through, they
swing it in a very flat.
Speaker 1 (15:58):
Plane as horizontal.
Speaker 2 (16:01):
Horizontal, right, yeah, That is not a very efficient plane
to use when you're throwing the ball on a very
vertical plane. So a very common low hang piece of
fruit feedback that comes out of the reports is having
pitchers just try to rotate their lead arm pull with
their lead arm in a more vertical plane to better
(16:21):
match what their torso is doing, a better match with
their pitching arm is doing.
Speaker 1 (16:26):
That's a good one. I feel like that one's so
simple that you don't want it to get out that
everybody ell to start looking at it.
Speaker 2 (16:31):
No, I mean really, I mean like it's this has
happened when I went to talk to a team and
we talked about some pieces, you know, some low hanging fruit,
and they're like, okay, great, we'll take the lead arm thing,
will implement it everywhere. And I'm like, well, what about
like the other ten pages of the report.
Speaker 3 (16:49):
Good with the lead arm thing.
Speaker 1 (16:52):
Thanks by so for you. The end of the train
is the report. But that report goes to the coach, right,
and so presumably the meaningful change hasn't happened yet, right,
It has to somehow get from the coach to the picture.
And like, I know that piece of it is not
your business now, but it was kind of your business
when you were at the Dodgers. Presumably you're familiar with
(17:14):
it now, Like, how does that piece of it work?
Is it like the pitching coach is like reading from
the report to the picture. I imagine not, but I
don't know.
Speaker 2 (17:20):
No, definitely, definite, definitely not. Even at the Dodgers, my
role was not being the one to coach the players.
Speaker 1 (17:32):
It's like, whatever you do, don't talk to the pictures. Man,
go back to your computer.
Speaker 2 (17:36):
Yeah no, no, I mean thankfully I got to be
in the in the room as you know, dark Walld,
the interaction is happening. But I think that is the
the art of coaching that is so important is understanding
the picture and how the pitcher thinks about themselves and
giving the right feedback to have the picture do the
(18:00):
thing that you that you want them to do.
Speaker 1 (18:02):
Uh huh. Knowing how to talk to a player in
a way that is not generic. Presumably different pitchers need
to hear different things, even if the outcome is the same, right.
Speaker 2 (18:12):
I mean, there's a there's a classic like debate in
baseball of like do you swing down on the ball
or do you swing with an uppercut? And in reality,
like the batpath is an arc, the path goes down
and then the path goes up. But some coach, some
players respond better when a coach will say swing down
on the ball, and some players spawn better when a
(18:35):
coach will say, you know, have get a little bit
more uppercut, do your swing. But in reality, you know,
the bat goes down and the bat goes up. So
it's like really understanding what is the player what helps
the player the most?
Speaker 1 (18:45):
So I heard you use this phrase in another interview
that I think is kind of what you're talking about here,
And it's feel versus real? What is that? What is
feel versus real?
Speaker 2 (18:55):
So it's exactly what we're talking about. Is sometimes with
the apt let feels like they're doing is not.
Speaker 3 (19:03):
What's actually happening.
Speaker 2 (19:05):
But if you understand what the athlete feels like they're doing,
you can give feedback that interacts with how they're feeling.
So if they feel like they're swinging down on the
ball and you give them feedback related to that, even
if they're actually swinging with an uppercut, you know, the
important thing is like how do they feel and how
do you give them feedback related to how they feel,
(19:26):
which then impacts is real. But it's understanding the interplay
between the feel and the real.
Speaker 1 (19:32):
Yeah, it's wild that, like there is there is a
human being doing a thing, and then there's this huge
industrial machinery of your company and the team and all
of these scientists and all these cameras and computers that
are trying to get this human being to change their
behavior in a very subtle way.
Speaker 3 (19:52):
Yeah, exactly.
Speaker 1 (19:53):
It's a behavior that is in many ways intuitive right,
it's sort of partly conscious but partly intuitive him like
there's a really interesting human being at the center.
Speaker 3 (20:05):
Of all of this.
Speaker 2 (20:06):
Yeah, And I think that's also why it's so important
to have the coach in the loop, because they understand
the human being even beyond just like the feel versus
real aspect of like did the athlete not get a
good night's sleep last night, then maybe today is not
a good day to give them feedback. Are they going
through challenges, you know, with a significant other, are they
(20:27):
going through challenges in other ways? Or today are they
really fired up? So today is a really good day
to give them feedback. It's like understanding the human being.
I'll give him a shout out. Connor McGuinness is the
assistant pitching coach right now for the Dodgers, and he
was so good at this. He would always talk about
he never felt comfortable truly coaching a player until the
(20:49):
player trusted him, until he felt like he had a
good enough relationship with the player with the player would
feel comfortable taking his feedback.
Speaker 1 (20:57):
Like start with the player as a human beings, Start
with the player and get to get to.
Speaker 2 (21:02):
And this is why I think it's going to be
really really difficult to have a product that goes direct
to a player. We've dabbled with that, you know, and
lots of companies have dabbled with film yourself with your
iPhone and you get some feedback, you know, on your movement.
But I think there's so much subjective stuff that goes
(21:23):
into what we're talking about, how does the athlete move
and how do they feel like they're moving, that I
think it's going to be really hard to solve the
challenge of giving an athlete feedback without a coach.
Speaker 1 (21:36):
In a minute, Jimmy's work in the NBA and why
figuring out how to help NBA players shoot better is
actually a really hard problem. What are you doing in basketball?
Speaker 2 (21:55):
Basketball is very very cool because it's a slightly different
channe In baseball, like we've been talking about, the challenge
for a pitcher is mostly just maximizing efficiency, or even
for a hitter, you know, they're reacting to the pitcher,
but they're still trying to swing as hard as they
can and hit the ball as far as they can.
(22:18):
So basketball is very different because you got a target.
You're not trying to do this thing as hard as
humanly possible.
Speaker 1 (22:25):
The target is the hoop. The targets to be clear, the.
Speaker 3 (22:28):
Target is the hoop.
Speaker 2 (22:29):
So that's a really interesting kind of like motor control
problem of no matter where you are on the court,
how good are you at getting the ball to do
what you want it to do. We've been finding that
there seems to be lots of trade offs that good
(22:49):
shooters are making regarding like when do they release the
ball in the course of their jump, how high of
an arc do they use when they release the ball,
how high they have their release point when they.
Speaker 3 (23:01):
Release the ball.
Speaker 2 (23:02):
So there's all sorts of trade offs that these shooters
seem to be making related to how good they are
at controlling their own jump, controlling their own velocity, where
they are on the court, how close the nearest defender is.
It's it's a very different problem.
Speaker 1 (23:18):
Sounds way harder, sounds way way harder, is that right
for you? Harder for you to sort of solve to
write a report that says, do this different thing and
you'll hit a higher percentage of your shots.
Speaker 2 (23:29):
Right exactly? Yeah, And which makes it which makes it fun.
I love solving hard podcasts.
Speaker 1 (23:35):
What have you solved in basketball so far?
Speaker 2 (23:38):
The big the first challenge that we had to solve
was the scale challenge in basketball. There isn't quite as
much there aren't quite as many games in basketball, but
the data is a lot harder to parse because the
events aren't as distinct. It's not like it's not like
this is a shot, I mean only for free throws.
Speaker 1 (23:59):
It's a more continuous.
Speaker 2 (24:00):
Continuous motion. So the first big challenge was how do
we even just isolate the events that we care about.
Speaker 1 (24:06):
Like what is time? When does a shot begin? When
does a time equals zero for shot?
Speaker 2 (24:11):
But kind of debatable, right exactly. So that, yeah, that
was the first big challenge that we had to solve.
Was just sort of like the data engineering challenge. And now,
like I said, our reports are more than telling you,
you know, how to be more or less efficient. It's
trying to surface the trade offs that you're making. Where
(24:32):
in your jump are you are you releasing the ball,
how high is your release point? What kind of arc
are you using? And how does that compare to other
arcs you could be using?
Speaker 1 (24:41):
What like what what are the trade offs?
Speaker 2 (24:44):
A really really interesting trade off to me is how
much arc are you putting on the basketball? Not just
to like evade a defender. But there's a trade off
where if you shoot the ball at a highhigher arc,
you have to use more velocity to get the ball
to go all the way to the rim.
Speaker 1 (25:07):
Right, because it's going to travel farther in total in space.
Speaker 2 (25:10):
Right, And if you are not the most coordinated human,
it might be harder for you to add more velocity
in a really in a really precise way. So the
more arc you have, the more prone you can be
to what we would call like velocity errors overshooting undershooting.
The advantage you get when you create more arc is
(25:33):
if you if you imagine the ball coming down from
that arc and the angle the angle with which it
approaches the rim, it approaches at a steeper angle, which
means you literally have more rim to aim at.
Speaker 3 (25:44):
So if you're hot, so if you shoot.
Speaker 2 (25:46):
Higher, you know this is a steph Curry thing. He
has a really high arc. Presumably this is the hypothesis,
because he's one of the most coordinated humans on the.
Speaker 1 (25:55):
Planet, so he sea.
Speaker 2 (25:59):
So he can use a really high arc because he's
really good at controlling his velocity output. Oh huh, so
he can really dial in how hard he releases the ball,
which means he gets the advantage of having more rimmed
to aim at, where as somebody who's bad at controlling
their velocity output when they try to aim higher, they'll
just overshoot an undershoot.
Speaker 1 (26:17):
So is the notion, and this is something of an oversimplification,
but that for any given level of coordination, there is
some optimal arc, and the more coordinated you are, the
higher the optimal arc would be for you setting aside defense.
Speaker 3 (26:33):
Maybe that's the hypothesis.
Speaker 1 (26:35):
Yeah, I mean that seems like where what you were
saying goes exactly.
Speaker 2 (26:40):
Yeah, that's the hypothesis. So that's what we're trying to
look into.
Speaker 1 (26:43):
Okay, I'll be curious to see what you figure out.
Are free throws easier? Did you think of starting with
free throws?
Speaker 3 (26:51):
Yeah?
Speaker 2 (26:52):
Right, right now. Honestly, the phase we're at in basketball
is mostly just collecting a lot of data. So you know,
a starting pitcher will you know, throw ninety pitches in
a game, and now you have a sample size of
ninety pitches that are all the same, whereas a basketball
shooter only has a couple of free throws in a game.
You know, we're working on ways with teams of collecting
(27:15):
data in a practice setting, so getting a lot of
this data in a bigger chunks. But really at this
point it's collecting a lot of data so we can
do some of this research to explore some of these hypotheses.
Speaker 1 (27:27):
Huh. So it seems like in basketball you're where you
were ten years ago or something in.
Speaker 3 (27:33):
Baseball, right exactly.
Speaker 1 (27:35):
So basketball is sort of one kind of frontier. It
seems like one thing you're trying to figure out and
haven't really cracked yet. What are some of the other
frontiers the other things you're figuring out, whether it's in
baseball or in the fundamental technology or whatever. What are
you working on?
Speaker 2 (27:54):
We want to try to have a computer vision be
even more accessible. You know, there's been a lot and
a lot, a lot a lot of improvements over the
last ten years in computer vision where you can do
really good motion capture with just your iPhone, but still
(28:17):
for certain specialized movements, pitching, shooting, things like that, there's
still have little ways to go to get really really
good data straight from your iPhone. So that's one of
the frontiers, is like continuing to try to help understand
how to make computer vision more accessible. Another one is
(28:40):
more fitness based analysis. You know, it's interesting to think
about companies like Mirror and companies that have tried to
give people feedback and like a fitness environment, But how
do you give someone or how do you give like
a strength and conditioning coach good feedback that can be
(29:00):
used in a weight room setting. Yeah, and then continue
to explore other emotions and other sports, Like football is
a really interesting one because a lot of football is
interacting with other humans. Indeed, yeah, I mean that's obvious,
but like, how do you get a takeaway from like
(29:21):
two linemen interacting?
Speaker 1 (29:24):
Ye, things, but that one I wonder. I mean, it
seems like if you think of the line, you know,
in football, it's so they're so on top of each other,
the defensive line, of the defensive line, that I feel
like vision might not be what you want. You might
want sensors, right, you might want pressure sensors in the
lineman's clothes or something. I don't know, I'm just making
that up, but like it seems like that might be
(29:45):
more useful, just because it's hard to see what's going
on in the line.
Speaker 3 (29:47):
Yeah.
Speaker 2 (29:48):
Yeah, yeah, except professional athletes don't like wearing random.
Speaker 1 (29:52):
Things, well are aren't people trying to make sensors like
woven into the clothes. I mean, I feel like there
are ways you would just be putting on your jersey
or putting on your paths or whatever and they would
have the sensors built in.
Speaker 3 (30:05):
Yeah. Yeah, one hundred percent.
Speaker 2 (30:06):
There's lots of really cool technology of that is you know,
you know, microscopic sensors that are just woven, woven into
clothing for sure.
Speaker 1 (30:16):
So so let's talk for a second more about the
consumer side. You sort of touched on it and moved on.
I mean, is that are you actively working on that
or is that just like yeah, it kind of seems interesting,
but not for now. We're too busy, like what's what's
happening on the consumer side.
Speaker 2 (30:33):
We're not actively tackling in the consumer side right now.
And that the reason why we started with professional sports
is one it's because like it's what I know, you know,
I work for the Dodgers, but also because the value
proposition of what we're doing is so impactful. You know, yeah,
you know, you understand, you try to understand, like the
(30:54):
relationship between people have tried to put numbers on this,
it's the people have estimated, it's in the millions of dollars.
But the value of adding one mile an hour of
fastball velocity to a picture, you know, people have valued that,
We have valued that in millions of dollars.
Speaker 1 (31:10):
Well, sure you will tell you millions of dollars, But
what is the like, I don't know what's a what's
a what's a top picture make? These days? I don't
even know anymore.
Speaker 3 (31:20):
I mean, you want to talk about show.
Speaker 1 (31:23):
Half a billion, hundreds of millions, half a billion? Yeah,
so so right, so so the marginal benefit has a
very large value. Yah a million dollars against one hundred
million dollars, like one percent better. If they're making a
hundred million dollars, it's worth a million dollars presumably.
Speaker 2 (31:40):
Yeah, And we start to get the pro sports teams
to believe.
Speaker 1 (31:43):
That, well, how many how many pro sports teams are
paying you at this point, about uh.
Speaker 2 (31:51):
Close to ten in Major League Baseball and a couple
in the NBA.
Speaker 3 (31:55):
The NBA is a lot newer.
Speaker 1 (31:57):
And how big is the field? Like, what's sort of
the state of play in the field of I don't
even know what to say. Biomechanics as a service seems
like a niche construction of it. But what would you
say sports analytics? I mean, I guess that's not quite right.
What how do you construct the broader field?
Speaker 2 (32:15):
Sports analytics is definitely a part of it. The data
that we provide is novel or is different than like
traditional sports analytics. So we don't really have a lot
of companies as competitors. Honestly, our biggest competitors are teams
(32:38):
wanting to try to do this type of thing internally.
How you know, hire a bunch of data engineers, hire
a bunch of software engineers, hire people with biomechanics backgrounds,
and try to build out these pipeline processing pipelines themselves.
Speaker 1 (32:50):
Does every team have like a somebody with a PhD
in biomechanics working for them now?
Speaker 3 (32:55):
In baseball? Yeah?
Speaker 1 (32:57):
Wow?
Speaker 2 (32:58):
In basketball and not Yeah, but they're starting to.
Speaker 1 (33:02):
So I know people, I mean, I think in general
baseball fans like to complain, but so one of the
things they've complained about lately is the way analytics more
broadly made the game more boring, right, like the shift
and changing pictures more frequently and whatever else people complain about.
Are you do you fit into that at all? Uh?
Speaker 3 (33:28):
That's a good that's a good question. Some people.
Speaker 2 (33:35):
Some people complain about how hard pictures are throwing these
days because it creates more strikeouts, and people think strikeouts
are boring.
Speaker 3 (33:45):
So maybe, yeah, so.
Speaker 1 (33:47):
Maybe you need to get better at helping hitters. Really
you're out that way, you can even at back up, all.
Speaker 2 (33:53):
Right, And that's what we talked about takeaways four Hitters
are harder because they're reacting to the picture.
Speaker 1 (33:59):
So if you think about the field, what your company
say in five years, yeah, whatever is your kind of
medium term future that you think about, what is the
company in the sort of the world, the sports world
that you're interacting with look like at that time and
say whatever, five years, ten years.
Speaker 2 (34:18):
What I hope is that what we are trying to
foster is an environment where coaches have really incredible tools
at their disposal to understand how an athlete moves. So,
you know, we talk about the very beginning where sort
of the still more or less the state of the
(34:40):
art is a coach just looks at an athlete, watches
video of an athlete, and tries to give the athlete
feedback regarding what they see on the video, what they
see with their eyes. We hope that the standard becomes
you use an analytical tool to help you understand how
the athlete is moving and to really like level up
(35:02):
your coaching because now you have this objective information about
how the athlete is moving. I kind of I kind
of make the analogy related to just radar guns. Before
radar guns were a thing, a coach would just like
look at a picture and be like, oh, that looks
pretty fast, you know, make an adjustment, and I think
that looks a little faster. But then radar guns came out,
(35:27):
and you could actually measure how fast the picture was throwing,
and you could actually measure if the picture is getting
throwing the ball harder based on your feedback.
Speaker 1 (35:35):
Yeah, and now you're you're doing that but in a
in a way more complex way.
Speaker 3 (35:41):
Exactly.
Speaker 1 (35:42):
Yeah, we'll be back in a minute with the lightning round.
Let's do the lightning rounds. Let's start with a few
(36:03):
baseball questions. Who's the most underrated picture of all time?
Speaker 2 (36:08):
Whoa underrated picture of all time? Oh my goodness, I
don't know if I can give you one that's like
all time, because I don't know if that's fair. I'm
sure I'm not thinking of everybody of.
Speaker 1 (36:24):
Your lifetime, of your lifetime.
Speaker 3 (36:26):
I grew up a hardcore Red Sox fan.
Speaker 2 (36:29):
I grew up in Rhode Island, and the first one
that comes to mind mostly in the Red Sox atmosphere,
but I wonder if you could make a broader argument
was Tim Wakefield, who was a knuckleball pitcher for the
Red Sox and what made amazing physics amazing physics and aerodynamics,
And the reason being is he just did so many
(36:53):
things for the Red Sox, ate up so many innings
and was so effective closing, starting, whatever, But he never
got incredible recognition because it was a knuckleball that was going,
you know, fifty five sixty miles an hour.
Speaker 1 (37:07):
What's one thing you would change about baseball to make
it more popular?
Speaker 2 (37:13):
I do feel like actually the changes that are being
made are good ones, in like reducing the amount of downtime.
Speaker 1 (37:23):
A pitch clock, it's one, is that the way you're
thinking of?
Speaker 2 (37:26):
Or yeah, yeah, yeah, exactly, yeah, a pitch clock. The
thing that's challenging for me as a biomechanist is when
you reduced the amount of time that a pitcher has
to throw, you theoretically could introduce more fatigue, which theoretically
also introduces more injury risk. So this is something that
we've been thinking about. Is like, So for me, while
(37:46):
I like that change that baseball is making to make
the game, to speed the game up, I think the
pitchers also need to train a little bit differently. Oh,
that's to be able to better withstand the shorter rest time.
Speaker 1 (38:03):
Are there aspects of your work and the changes you've
seen over the course of your career that illuminate sort
of broader changes in computer vision and AI more generally.
Speaker 2 (38:16):
Yeah, In particular, the most important one has been the
improvement in computer vision, which because computer vision at its
core is artificial and intelligence neural networks, and as those
as that that technology has gotten better and better, you know,
the latest and greatest people always talk about like the
Transformer model really changed AI. I mean that changed computer
(38:38):
vision too, Like lots of the modern more modern like
computer vision models are based on transformers.
Speaker 1 (38:44):
And which, to be clear to the Transformer model is
what gives us chat GPT, right, The T in GPT
is transformed, right, So how has it affected the computer vision.
Speaker 2 (38:53):
Side making the models more accurate and more efficient? It
used to be you know, a couple of years ago
when I try to run a computer vision model on
my laptop, like it could take an hour just to
like analyze one pitch, one video, and now it takes
a matter of seconds.
Speaker 1 (39:12):
And so what is the what is the bigger implication
of that? Beyond your beyond your work?
Speaker 2 (39:19):
More and more data is available regarding how people move,
you know, like when when I first started, it was
really hard to have data in a baseball game. Now
every major league game, every minor league game, every NBA game,
maybe every G League game, every w NBA game, you know,
every single uh basketball and baseball game, you know, more
(39:44):
or less is now like being recorded with computer vision
to get the three dimensional data about how people are moving.
Just lots and lots of data on how people move.
And this is really impacting. I think lots of fields.
In particular, I think like self driving cars, robots that
are meant to like interact with the world, all rely
(40:05):
on computer vision models. I mean, I think one of
the coolest things about how cars do this sort of
thing is not only do they have to understand where
a person is now, but they're really cool models that
they take where a person is now and the last
like ten seconds of what that person did and try
(40:28):
to predict all the different things that the person might do.
They might run across the street, they might jump out
of the way, they might jump forward, you know, they
might run and chase a soccer ball.
Speaker 1 (40:38):
I mean, my sense is all of the hard edge
cases in self driving cars. Basically, the reason we don't
truly have self driving cars yet is because people are
so hard to understate. Yeah, right, Like if the world
was all self driving cars, then it would be a
solved problem, right, Like the machine could understand what other
machines are going to do. But people, human drivers, human
(41:00):
pedestrians are strange and very hard for machines to understand.
Speaker 3 (41:06):
Yeah.
Speaker 1 (41:07):
Yeah, it's like they need a coach. It's like the
coaching problem again. We found your SoundCloud. Oh yeah, so,
Jimmy Buffett fans are called parrot heads. What are Jimmy
Buffy fans called?
Speaker 3 (41:26):
I never thought about it.
Speaker 1 (41:31):
You have a song called Let's have some Fruit parentheses
the fruit song is fruit a metaphor.
Speaker 3 (41:41):
Leave it up to your imagination. Fair.
Speaker 1 (41:45):
Jimmy Buffy is the co founder and CEO of Reboot
Motion Swanson swe Today's show was produced by Gabriel Hunter Cheng.
(42:06):
It was edited by Lyddy Jean Kott and engineered by
Sarah Bruguer. You can email us at problem at Pushkin
dot Fm. I'm Jacob Goldstein and we'll be back next
week with another episode of What's Your Problems
Popular Podcasts
1. Las Culturistas with Matt Rogers and Bowen Yang
Ding dong! Join your culture consultants, Matt Rogers and Bowen Yang, on an unforgettable journey into the beating heart of CULTURE. Alongside sizzling special guests, they GET INTO the hottest pop-culture moments of the day and the formative cultural experiences that turned them into Culturistas. Produced by the Big Money Players Network and iHeartRadio.
2. Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations.
3. Crime Junkie
If you can never get enough true crime... Congratulations, you’ve found your people.