Latest / The Future Herd / 18: The Rise of the Computational Breeder with Mohsen Yoosefzadeh Najafabadi

Transcript

18: The Rise of the Computational Breeder with Mohsen Yoosefzadeh Najafabadi · The Future Herd

0:00
Jesse Hirsh: Hi, I'm Jesse Hirsh.
0:03
Welcome to The Future Herd.
0:12
Today we get to a talk.
0:14
Today, we get to talk about a topic close to my heart.
0:18
Artificial intelligence and agriculture, and in particular programmatic breeding,
0:25
otherwise known as computational breeding.
0:28
That's where my new friend Mosen and one of the pioneers in the field not
0:33
only helps us understand the way that AI can empower farmers, researchers.
0:39
And policy planners, but also the courage, the learning, the curiosity
0:45
required to be a leader, not just in agriculture, but in technology as well.
0:51
In today's subject, we're gonna get into the weeds in terms of things
0:55
like Bean, GPTA, custom AI for plant breeding, in particular dry beans.
1:03
But we're also gonna talk about some of the challenges, some of the
1:06
opportunities, some of the developments when it comes to mashing together some
1:11
of these powerful tools from data science and machine learning with the wisdom.
1:16
And intuition that we find in agriculture and AgriFood.
1:22
I've been waiting a long time to talk about AI in the concept of the
1:26
future herd, and in that regard, Mosen does not disappoint at all.
1:32
I did my best to try to limit, uh, he and my potential to nerd out on
1:37
these very interesting subjects, and I think we perhaps accomplished it well.
1:43
Maybe giving you some key words that you might search to learn more.
1:48
This is really just the tip of the iceberg when it comes to
1:51
exploring how this technology is shaping the future of our sector.
1:55
And we will definitely have future episodes that get into it.
2:00
So think of this as both a kind of introduction and overview as
2:05
well as a specific case example when it comes to breeding beans.
2:10
Alright, let's listen in.
2:13
Mohsen, welcome to the Future Herd.
2:16
Mohsen: Thank you so much for having me, Jess.
2:18
Jesse Hirsh: Now, I gotta say you're our first guest in this podcast who I
2:22
can finally talk to AI about, so I'm particularly excited about that today.
2:28
Uh, but the first question that I throw out to every guest as a kind
2:32
of abstract, what's on your mind, what does the future mean to you?
2:39
Mohsen: Oh.
2:40
That's a great question.
2:41
Basically AI and future, huh?
2:45
you, you know, to me the future depends on which part of life we are talking about.
2:51
So I can.
2:53
Explain future in different aspects of my life.
2:57
So let's say in my professional work, the future means planning, improving
3:03
and trying to stay one step ahead.
3:06
No, not at least, you know, or, or at least not two step behind.
3:10
You know, this is something that I can just articulate that.
3:14
future in my professional life is about learning from past.
3:20
And gain much experience and prepare ourself for the future.
3:26
So if I can do this today, I can make my future better and perfect.
3:32
Right?
3:33
So I like to run and something people like sometimes tell me about
3:39
the future and they are sometimes getting scared of these fast paced,
3:43
changing that happening these days.
3:45
But you know what I love?
3:47
I love these kind of fast paced changes and I wanted to embrace it.
3:51
So this is.
3:52
The meaning of the future in my, uh, actually professional life, but you know.
3:59
In a broader sense, like politics or society, if you ask me about it,
4:02
you know, I feel that future looks a bit like the past because history
4:06
has funny, like, you know, has a funny habit of repeating itself.
4:11
So, or even in my personal life, if, if you ask me about what does it
4:15
mean, what future means in my personal life, it means opportunity because.
4:18
Finally I can lay down and let the future, let the robots and everything,
4:22
do my, do my chores and every other things, you know, but yeah.
4:27
So that's, that's a different meaning, you know, that I have for the future.
4:31
Yeah.
4:32
Jesse Hirsh: Right on.
4:32
Fantastic.
4:33
And, and I think you, in that answer kind of gave us hints as to why AI
4:39
and robotics is an area of interest.
4:42
But let me ask the inverse, uh, why agriculture, why plants?
4:47
Uh, what was it about that side of science that not only did you say, Hey, let's
4:53
see how AI and this kind of connect.
4:58
But these days, AI, people like yourself, people who have that
5:02
curiosity are in high demand.
5:04
You could have picked any sector, you could have picked anywhere to focus.
5:08
Why plants?
5:09
Why agriculture?
5:10
Why beans?
5:12
Mohsen: Wow.
5:12
No, that's a great question, Justin.
5:14
The point is the time that I decided to work in agriculture was only because
5:19
of one reason, and the reason was.
5:21
I grew up in a farm and I used to go to the farm with my dad, and I remember,
5:25
you know, all the time my dad, you know, we're so happy at the farm and
5:29
he tried to just make me happy on the farm and just ask me that, Hey Mo,
5:34
do this, do that, help me with that.
5:36
And be honest.
5:37
On that time, I hated to do that because I was just thinking,
5:40
okay, why should I do this?
5:42
Right?
5:43
I, my passion was like, you know, novel reading, novel books, playing
5:47
music, those kind of things was not actually into the agriculture.
5:52
gradually I realised that everything that we are doing
5:57
are rooted in agriculture, food.
6:00
Uh, even our future, uh, depends on the agriculture.
6:03
So if I
6:04
Jesse Hirsh: might,
6:05
Mohsen: to survive and read novel book, if I wanted to play music, I need to
6:09
have something to eat and this is coming from the agriculture, how can I like
6:14
Jesse Hirsh: I'm making work.
6:15
Mohsen: that there are, there is enough food in the future.
6:18
You know what, that was the simple question that I've
6:21
tried to answer on that time.
6:23
I started to do undergrad on horticultural sciences and.
6:28
In the horticulture, we are working with a very small scale rather than like
6:33
working on the large scale field area.
6:35
So on this small scale I was working on watermelons and Q Cortes, like,
6:40
you know, cucumbers, watermelons, and.
6:43
I've, I started to just enjoy actually going to the farm because I, on that
6:48
time I had this kind of like, you know, things to answer in my mind and I had this
6:54
kind of goal, so I went to the field on a stick, you know, made my hand dirty in
7:00
the field, and I just realised, okay, how cool it is to work on the agriculture.
7:04
And then later on.
7:05
I started thinking, okay, what can I do to speed up this productivity?
7:10
What can I do to ensure the food security in the future as a graduate student?
7:15
What can I do?
7:15
How can I play an important role in this area?
7:19
And I, I was just thinking, and I found that, okay, maybe I, we all gathering
7:24
all the data, we all collecting everything, how about just the get
7:29
the best juice out of whatever we are producing in terms of the data.
7:34
And then that was something that I started to dig more into the statistics
7:39
and then gradually machine learning.
7:41
And then when I get into the PhD and I was started to work on a
7:45
larger scale field on soybean.
7:48
Which is the agronomy like, you know, crop.
7:50
I've realised, okay, now it's time to apply those things that I was just
7:55
imagined in my, like, you know what?
7:57
Now I can make it applied into the actual agriculture setting.
8:02
that was the time that I started to apply these kind of machine
8:06
learnings and like AI and more sophisticated statistical algorithms.
8:12
Jesse Hirsh: Now, before we kind of get into your particular research, tell
8:17
me about, for lack of a better phrase, that the ecosystem of researchers that
8:23
were alongside you as you did that.
8:25
Because on the one hand, you are breaking new ground, right?
8:28
Digitally and physically, and, and, and I'm curious.
8:34
You know who you were looking for in terms of inspiration, right?
8:37
Because you, you're kind of on the one hand inventing it as you go along.
8:42
But on the other hand, it is an exciting industry.
8:45
It is an exciting research ecosystem.
8:48
So where were you drawing inspiration from?
8:50
'cause part of you answer was your dad, right?
8:53
And like, getting you back on the farm and thinking.
8:56
But, but intellectually, scientifically, where, where were you getting clues from?
9:00
Where were you getting inspiration from?
9:03
Mohsen: Yeah.
9:03
You know, before I answer this question, you know what?
9:06
that I started to work on machine learning, it was not as easy to
9:09
say, Hey, I'm computational plant breeders, because I remember the first
9:13
time that I. Remember, I remember the first time that they gave the
9:16
presentation, were just telling me, okay, Mo, you are living on your dream.
9:21
It's not going to happen.
9:22
Like, you know, you are just flying drone.
9:25
Take some pictures using neural networks.
9:28
Ai, what are you doing?
9:30
You know, just do some real work.
9:32
You know, do B like a actual plant breeders.
9:35
And I remember when I even graduated, people called me, okay, Mosen
9:39
is the computational biology.
9:40
It's not actual breeder.
9:42
Because they had this kind of mindset, and you know what?
9:45
They were right.
9:46
You know, on that time, you know, no one was predicted what happened in the future.
9:50
And you know what?
9:51
Sometimes.
9:52
What I'm trying to do, I'm just trying to, I, I love to read novels.
9:56
I love to read, you know about people's work.
9:58
I love to, I love to read and I read, so read so many books, so many
10:02
journals, and one of the people who inspired me a lot is Dr. Rex Bernardo.
10:08
So he's a plant breeder and I love reading his journal.
10:14
He, his, you know, uh, papers, I love to attend his seminar
10:18
and he's one of the people I, I usually follow as a plant breeder.
10:23
And that was just, you know, I had a chance to talk to Rick Bernardo a
10:27
couple of years ago and I asked him that he, if you, if he's available
10:31
to meet me in person, and he did so.
10:34
Like, you know, sorry, meet in virtual, and he did.
10:36
And we talk about so many different subjects and I found
10:40
that okay, we are very close.
10:42
Sometimes we are trying to adopt new technologies, but sometimes we are
10:47
going one step back and thinking, okay, is it really a good technology or not?
10:52
If it's good, continue and then.
10:54
How about adding this?
10:55
How about adding that, right, to make it something better.
10:59
Jesse Hirsh: right.
10:59
Mohsen: So that was something that inspired me to work in this area.
11:03
Another one is I love sometimes, you know, to, not sometimes, but most of the
11:09
times I'm trying to challenging myself.
11:12
And when I'm seeing that, you know, people are just asking me,
11:15
Hey Mo, why are you doing this?
11:17
And have this kind of like, you know, things in my mind
11:21
that, okay, I'm doing right.
11:22
I wanted to work and make it applied and finally let people know that,
11:28
hey, is something that I told you it works and now it's working.
11:33
Right?
11:34
So that was, and we call it self inspiration, you know, so just had these
11:37
kind of things in my mind to just follow whatever people call it as a dream.
11:42
I wanted to make my dream true true.
11:44
So, yeah.
11:46
Jesse Hirsh: And, and the concept of the computational breeder
11:50
is revolutionary in of itself.
11:52
And, and I empathise with the idea that when you're too far ahead of
11:56
the curve, you appear as a fool.
11:58
And it's not until after the fact that people respect your wisdom.
12:02
So, so.
12:03
We are now at that point, thankfully.
12:06
Uh, but I imagine it was a bit of a difficult path for you to get there.
12:10
But the paradox is, to your point, we seem to be at a moment where
12:15
people are starting to accept that our entire world is programmable.
12:20
That there are elements to our world that we can engage with on the
12:24
level of code and of programming.
12:26
So take a moment to unpack what.
12:29
Programmable breeding is 'cause I suspect all of the listeners right now, unless
12:34
they've already Googled you while they've started the show, have never heard that
12:38
phrase before and are still wrapping their head around what that might be.
12:43
Mohsen: No, that's a great question.
12:45
Just so the point is, uh.
12:48
I can just, you know, make an example of what I'm doing
12:51
here at University of Guelph.
12:52
So I'm working on two different areas, driving in breeding
12:56
and computational biology.
12:58
These two subjects are very far from each other at the beginning, but
13:01
at the end they are super close.
13:04
So in the traditional breeding, what we are doing is we are going to the
13:07
field and try relying on our breeder's eye, seeing if the plant is good,
13:14
they has a good uprightness, you know, it's like, you know, looks healthy.
13:18
We are, pick it up.
13:19
And then grow next year and a year and a year.
13:21
And we try to just, you know, gather more data, more information.
13:26
those are usually done manually.
13:28
And it's, we are significant.
13:31
Rely on our guts, on our feeling.
13:33
Right.
13:34
Which is perfect.
13:35
Which is good.
13:35
I love it.
13:36
But at some point.
13:38
We are adding, we need to add more information.
13:41
We need to see plant from different perspectives.
13:45
Like how about flying drones?
13:46
Take some picture from above and see if we are able to find something that
13:50
we couldn't see by the naked eye.
13:52
Right?
13:53
Or how
13:54
Jesse Hirsh: Not
13:54
Mohsen: you know, dig into the genetics of the plants?
13:57
Or how about working on the pure science part?
14:00
Of course we are able to do that is perfect.
14:03
But what's next?
14:05
So the next is.
14:07
We are having tonnes of data, tonnes of information, and
14:12
it's really hard to digest.
14:15
what would be next?
14:17
is to select the best and appropriate algorithms, right?
14:21
So we try to use ai, different types of AI and all those kind of things to digest
14:27
all the data that we are collecting.
14:29
But what next we get to the result?
14:32
Okay, that's perfect.
14:34
again, what next?
14:36
is we can use this result as to initiate new population and work on the same
14:44
pipeline and initiate a new population.
14:46
So if you are seeing, this is something that is started to do, like, you
14:51
know, as a programme, running as a programme and in each steps is
14:57
Jesse Hirsh: Is the.
14:58
Mohsen: of tradition the innovation.
15:01
With the coding and those kind of things, right?
15:04
All are linked, chained together this is the future.
15:08
I think, you know, to my knowledge, this is the future of the breeding and this is
15:12
what we call computational plant breeder.
15:15
I published a paper last year on Journal of Plant Physiology.
15:21
And I've just, you know, sometimes criticise actual my position because
15:25
my position is, uh, driving breather and computational biologist.
15:29
And I just mentioned exactly my position and my title in the paper and I said, Hey.
15:34
E, everyone can call me computational plant breeder instead of plant
15:38
breeding and computational biologists because we are using computational
15:42
biology to programme plant breeding.
15:45
So how about calling a person computational breeder?
15:49
Like you know, myself, I can consider myself as a computational driving breeder.
15:53
So anyway, this is the programmable breeding pipeline look like.
16:00
Jesse Hirsh: I am, uh, to the listeners, I, I am gonna do my best to resist nerding
16:05
out today and, and asking technical questions that indulge my curiosity,
16:08
but I'm gonna have to ask one right now.
16:11
One of the big things going on in the AI space are simulations and, and.
16:16
Mass simulations.
16:18
To what extent can you simulate some of the cycles that you described?
16:22
Because on the one hand, there's the practical, right?
16:24
The field tests and seeing how the plant performs in nature and
16:28
monitoring that data and repeating it.
16:30
But I have to assume you're also running simulations.
16:33
To come up with scenarios and hypotheses and other stuff to test.
16:38
I, I, for the non nerds who are listening, uh, describe the value that that plays
16:44
and the potential that that has for, for agriculture as a whole in terms of how
16:49
we've historically been limited to nature cycle, but now we have access to things
16:56
like digital twins that allow us to kind of simulate what a field is gonna do.
17:02
Mohsen: Yeah, I was going to touch about digital twins as well.
17:05
I'm so glad that you touched it.
17:07
So basically the point is, you know, uh, let me start it in this way.
17:12
What we are, what we used to do is just we grow thousands of individual
17:17
plants in the field and which with the hope of selecting one of them,
17:21
right, and the one superior of them.
17:23
Like let's say I'm growing around 200,000 individual plants and at one stage of
17:29
my breeding programme, and then I'm trying to shrinking down these numbers
17:33
that at the end, like after eight, 10 years, I'm reaching to one best.
17:38
So you can, you can see that how many plans here are sacrificing.
17:44
And why such these kind of things happen is because we wanted to
17:47
test it on different environments.
17:49
We don't have a good simulation analysis in the, in the like indoor to just prove
17:56
that what will happen in the field.
17:58
Right.
17:58
And we can, instead of growing 200,000 individual plants with
18:03
like spending so much time, money investing, so many things there.
18:07
How about running a good simulation and just shrinking down to a thousand?
18:12
Right.
18:13
So this is something that people, when
18:15
Jesse Hirsh: who
18:15
Mohsen: designing the jet and Gene, you know, they are doing that.
18:19
They
18:19
Jesse Hirsh: don't.
18:20
Mohsen: just, you know, let people just flying with the jet and gene
18:24
and see what will happen, right?
18:25
They, they are caring about people's life and so we have to care about plans.
18:30
Right in this case.
18:32
So the terms of the digital twin is something very new.
18:36
Very good.
18:37
And I think that's the future of the breeding programmes.
18:40
They need to run digital twins.
18:42
And we have it.
18:44
have it at University of Guelph.
18:45
What I'm doing is I'm trying to simulate that what if, if these plant with these
18:52
gene characters, with this genotype, like, you know, with the genetic background.
18:56
What if, if this plant exposed to these type of stresses, how the plants look
19:02
like, how the plants perform, right?
19:05
how plants perform.
19:07
If you are putting this in totally new environments and with
19:11
this soil type, these kind of, these are kind of simulation.
19:15
So recently I, one of the project that is going on right
19:19
now is my, in my programme is.
19:22
We try to predict what will happen in the future in different environments,
19:27
that they are mostly grown drive-ins and how we are doing that.
19:30
We actually have like the good history of growing drive-ins in those
19:37
regions, like El in, uh, in Ontario.
19:41
We are growing like, you know, in Woodstock in different areas, right?
19:44
We are growing drive-ins, different market classes of drive-ins there for many years.
19:49
So we have the data.
19:51
We have the environmental information like the total precipitation,
19:55
maximum temperature, minimum temperature, all those kind of things.
19:58
We have it.
20:00
what we have is we have the future scenarios.
20:05
So there are some anthropogenic climate change scenarios that is
20:11
available for scientists to use.
20:13
And this is based on different, like, you know, future, like different
20:17
scenarios that what if CO2 emission went high and goes up like, you
20:22
know, higher than current, right?
20:24
What will happen in terms of the temperature?
20:26
If the situation is normal?
20:28
What will happen if the situation is mild?
20:30
What will happen?
20:31
have all this environmental information year by year for the
20:36
next 50 years different locations.
20:39
Of course, it's not accurate, it's not a hundred percent correct,
20:42
but it can give us a good hint.
20:45
So if we developed a programme, everything based on the history, and then we feed
20:51
the future data there, we can predict how much this plant perform in new
20:57
environment with the new temperature.
21:00
So once we find it, instead of just blindly making cross, not blindly,
21:05
just making cross and selecting potential parental lines based on the
21:08
history, we are selecting patterns based on history and the future.
21:13
You know what?
21:14
So that's the main concept of digital twin.
21:17
And we can run it, we can test it, and we are doing it at, at the same time.
21:22
Yeah.
21:23
Jesse Hirsh: Right on.
21:23
And, and, and the capacity, like just the research questions alone, that, that kind
21:28
of thing enables, kind of blows my mind.
21:31
But let, let me come back to something we touched upon earlier.
21:35
Are you still blazing this trail alone or are there other people catching up like.
21:41
Give me a sense of the computational breeding landscape.
21:45
Are there other people who are clueing in to what MO'S been up to and saying,
21:49
Hey, that looks like fun stuff.
21:51
And what is the collaborative space like?
21:54
Like who are you able to work with?
21:56
Not just at the University of Guelph, but yeah, I assume that the more people who
22:01
are kind of ready to play, ready to dance, ready to engage in these types of methods,
22:06
the greater the value for all of you.
22:10
Mohsen: Oh yeah.
22:10
I have a very good colleagues, you know, all around the world.
22:14
Those are perfect.
22:15
You know, I, I'm proud of the community that I'm working in terms of the academia,
22:20
I don't want to talk only about University of Guelph, but you know, that, you
22:24
know, university of Guelph fostering collaboration, like, you know, and they
22:27
are fostering collaboration environment.
22:30
So we are having a highest collaborations between different
22:34
departments and others, but.
22:36
Aside from University of Guelph, I'm right now collaborating with different
22:40
researchers in Canada, like University of Laval, Ottawa, like, you know, I'm working
22:45
with Saskatchewan's, but, and also us like, you know, entire north, uh, America.
22:51
I'm collaborating mostly with some, there are, there are tonnes
22:54
of, you know, good breeders that they are working in this area.
22:58
And you know what?
22:59
All of them, like, you know, I, I had a chance to talk to a couple of them
23:02
and I know that, you know, we are somehow complete complement our jobs.
23:07
Like they are working, I'm working on these, uh, developing new algorithms
23:11
and everything, and they are using all the algorithms, like most of the
23:14
algorithms that we are developing here to test them on different locations.
23:18
And I'm doing the same thing.
23:20
So we are just trying to validate our algorithms.
23:24
We are trying to validate our pipeline, right?
23:26
And.
23:27
We are not only looking for the very small scale of the regions that we
23:32
are working, we wanted to expand it.
23:33
Right.
23:34
And right now I'm collaborating with some universities in France,
23:38
some universities in the uk, right?
23:40
Those peoples are also in interested, and you know what?
23:44
remember when I developed some of the algorithms and I published
23:48
these algorithms, I received very good and positive feedback.
23:51
Said, Hey, how you did that?
23:52
We are, we wanted to test it in our genuss.
23:55
We are working on grape.
23:56
Do you think that the algorithms that you develop into ripens with working grape?
24:00
And I said that, oh yeah, why not?
24:01
Let's check it.
24:02
Right?
24:03
And we check it.
24:04
We fine tuning all those algorithms and now it's work.
24:07
Right?
24:07
It works.
24:08
So basically, yeah, they are very collaborative.
24:12
Uh, environment all around the world.
24:14
We are, I, I, I can say there are tonnes of us, you know, to working in
24:20
this area, but there are a couple of us, some of us you know, are working
24:23
in this area in the computation as a computational plant breeder.
24:27
Yeah, I.
24:28
Jesse Hirsh: And at the risk of asking another nerd question, which, you
24:32
know, we will do our best to try to answer as accessibly as possible.
24:37
Talk to me.
24:38
You know, one of the, the research interests you have on your profile talks
24:42
about computational tools and AI platforms in that the, the subtext of everything
24:48
we're describing is there, you know, you, you need technology to gather data.
24:52
You need technology to analyse data.
24:54
Course the digital twin stuff is a whole other scale.
24:58
Um, without getting into the details of it, how accessible are these tools?
25:04
How available are these tools and how rapidly are they being developed
25:09
to your point of, you know, there's some computational breeders, but
25:14
how do we scale that number up?
25:16
Uh, in the sense that part of it is just access to the tools and access
25:19
to the literacy to use those tools.
25:23
Mohsen: Uh, no, that's, that's a very great question.
25:25
So basically I remember, uh, like, you know.
25:29
Eight to nine years ago, I was just focusing on developing different
25:32
algorithms to use whatever data that we are producing to make a prediction
25:36
and can help us to screen large number of genotypes, not large number of
25:41
actual plants, you know, in the field.
25:43
And we are able to detect diseases at the earliest stages, those kind of things.
25:47
And that was all limited to the prediction ability.
25:50
So we call them a predictive AI algorithms and there are tonnes of them, right?
25:57
Gradually we shifted from only working on the predictive to also
26:03
working on the generative ai.
26:05
And what does this generative AI means?
26:08
It means that, how about we are asking question and we are
26:12
getting an answer response by ai.
26:15
So AI can generate response for us.
26:18
So how AI can generate response.
26:22
It can be based on tonnes of things that we are feeding ai, right?
26:26
Jesse Hirsh: Right,
26:26
Mohsen: And I
26:26
Jesse Hirsh: and I.
26:27
Mohsen: thinking, okay, what kind of information do we have that I can
26:31
develop this kind of generative ai?
26:33
And I had a little search, I just wanted to share it with you.
26:37
So in on the year of 1970, there were around 12 to 15 publications on drive-ins.
26:47
Right now in 2026, actually 2025, like last year, was around 2,900 paper
26:57
that were published in Drive-ins.
26:59
you'll see that you know how much.
27:02
Scale were large, you know, right now is large.
27:05
The same for the conferences I've searched, or even the same for the word,
27:10
the actual driving word over the internet.
27:13
On 1970, it was 120 times the word of driving was repeated over the internet.
27:19
Jesse Hirsh: Right.
27:20
Mohsen: it's more than 6 million times.
27:24
So why this word is getting repeated?
27:27
And I've searched and I found out, oh yeah, there are tonnes of valuable
27:31
information there over the internet.
27:33
Even without there is a need for us to produce more data.
27:39
have tonnes of data.
27:41
So the challenge from the past last eight years, I think it's changed.
27:47
Changed from do we have the data to how we can find reliable and
27:52
relevant answers quickly, right?
27:55
Those type of things.
27:57
So on that time, I was just searching to see if there are any
28:01
like pipeline established that I can use it or if there is any Interac
28:05
inter integration, I can make it.
28:07
I couldn't find it.
28:09
I couldn't find it, started to do it and build everything from scratch.
28:14
So I started to develop something like a app called right now
28:18
is called it being GPT, right?
28:20
So this app being GPT, we collected more than 300 thousands indivi, like, you
28:26
know, literature all over the world.
28:29
And we indexed all of them.
28:30
We collected all the genetics.
28:33
All the phenotypes, all the agronomy, all the notes, everything that
28:37
was published in Drive-Ins and put it, put it in the being GPT.
28:42
And you know what, when you are right now asking question being GPT
28:47
search and finding relevant answer based on only these information, not
28:53
based on the general, like the chat GPT or the Clause and others, right?
28:57
So.
28:58
Jesse Hirsh: So
28:58
Mohsen: How
28:59
Jesse Hirsh: how we.
28:59
Mohsen: information.
29:00
It was really hard because, you know, so, so many of this information
29:04
were not publicly available.
29:06
We had to ask, you know, and so many things.
29:09
But right now I'm, I'm, I'm seeing that, you know, these type of retrieving in
29:13
information and gathering information is getting facilitated because
29:16
people right now understand that.
29:18
Importance of sharing these type of information and building
29:23
such as kind of apps, right?
29:25
So that was one of the app, the predictive AI was another app, right?
29:30
And now the challenge is how to make it hybrid, how to have the prediction
29:35
and actually validate whatever we are predicting by tonnes of information
29:40
out there through let's say Bing, GPT.
29:42
And this is the hybrid ai, right?
29:45
So.
29:45
I don't want it to go through the details and talk about all these type of things.
29:49
You know, I don't want it to be nerded here, but, you know, I, I, I'm getting,
29:53
I'm getting fascinated every time that I'm talking about AI and I can
29:56
talk for hours, but you know what?
29:59
Right now, the future of, uh, I think the future of, uh, ai, not ai, actually
30:06
AI in agriculture is how to make a hybrid ai, like the quantum hybrid ai.
30:12
And this is something that we are trying to go to toward
30:16
it and move toward it, right?
30:18
Jesse Hirsh: And I am gonna have to have you back on the show because I
30:22
too can talk about AI for hours and I think we're gonna at some point
30:25
organise a panel in which we together talk about AI and agriculture.
30:30
But I wanna a ask an important follow-up question around being GPT
30:35
from, from a kind of user perspective.
30:38
Because one of the, I, I think the appeals of like chat, GPT and clawed.
30:43
Is it makes complicated stuff accessible, right?
30:47
It makes it easier for people to talk about law or other complicated
30:51
areas and learn the terminology.
30:54
Does Bean GPT enable, say, bean genetics to be more accessible to a
31:01
student agronomist or a bean farmer who maybe has mixed scientific knowledge?
31:08
Does it enable that kind of, uh, accessibility in the kind
31:11
of learning curve to get people into computational breeding?
31:17
Mohsen: Absolutely.
31:17
Absolutely.
31:18
Jess.
31:19
You know, the point is that the main point of developing
31:21
BGPT is to make it accessible.
31:23
For a variety of people with different background, with different
31:27
knowledge, and it's not only designed for myself or like, you know, and
31:31
any other person specifically.
31:34
The point is when you are asking any question in being GPT, being GPT, try
31:38
to answer fully in a very simple way.
31:41
Let's say you are interested in a specific, like, you know.
31:44
Agronomic practise in dry pins, and you are asking this question,
31:47
okay, what would be the best herbicide in this case and when I
31:50
can apply this herbicide in my field?
31:53
So being GPT is trying to find relevant research and then try to make it like,
31:58
you know, uh, seem not the simple, but just make it more understandable and.
32:04
Provide the answer to you.
32:05
I can tell you that, you know, being GPT is not one app, is not one algorithm.
32:11
It's a kind of committee that consists of eight different algorithms.
32:15
We call it rag models, like we call it retrieval, augmented, uh,
32:21
generative, like, you know, models.
32:23
So these kind of models, each of them are trained for a specific.
32:28
Data, one of them trained only for literatures.
32:31
One of them is going to only search for the data.
32:34
One of them is going to only search for the agronomy.
32:36
One of them only going to search for the environmental data.
32:39
So many information when you are asking question, all these
32:43
people are discussing together and
32:46
Jesse Hirsh: And they.
32:46
Mohsen: threw out some of the words, some of the information, and
32:49
who collect all this information.
32:51
Is the open AI is the G-P-T-G-P-T collect all this information, make it simple,
32:57
make it ready and give it to the user.
33:00
So no matter if you are expert in the BG beam area, no matter to what kind
33:06
of knowledge, to what knowledge you have about being, no matter that what
33:10
you are going to search like in terms of, and you wanted to get BGBT, try
33:14
to provide you as simple as possible, as an understandable as possible.
33:19
Jesse Hirsh: Now I, I keep wanting to go to the environmental scan
33:23
questions, but do you know of other, uh, uh, uh, similar plant-based GPTs or
33:28
similar kind of agri centric, uh, gpt.
33:34
Mohsen: I've, I've seen a couple, actually, you know, they just recently
33:38
released a couple of GPTs, but.
33:41
And, but you know what?
33:42
I haven't had a chance to dig into all of them in detail, but what
33:46
I found that, you know, they are specialising in couple of data databases.
33:52
Like one of them are only looking for the literature, right?
33:56
Another gpt is only looking for some, like, you know, reports and
34:00
data and I couldn't find that.
34:02
You know, there is one, uh, like, you know, large language model.
34:07
it's not one, actually, it's a couple that each of them are specialising
34:11
on different algorithms, different database, and then when you are asking
34:15
question, your question is going to circulate among all these apps, all
34:21
these like, you know, algorithms.
34:22
So it's not one, and I couldn't find the same and the similar things in others.
34:28
Right.
34:29
Jesse Hirsh: I mean, this is where I will nerd out for a moment and say, this is
34:33
partly the revolution of open claw and the harnesses, right, of creating a software
34:39
layer that can access multiple models and combine that with a growing memory.
34:46
We're digressing.
34:47
We'll talk about that in the advanced episode.
34:49
But o on a related point, uh, as someone who I assume also
34:54
teaches a and also engages with students, tell me what's that like?
34:59
Like what are the students who are coming to you, what are their research interests?
35:03
And as a teacher, what are you trying to.
35:05
Get those students to focus on.
35:07
'cause so far I think I, I, my mind has been blown just thinking
35:12
about computational breeding and the kind of research you're
35:15
doing and the tools you're doing.
35:17
But part of what we do here on the future Herd is think about the future.
35:20
And of course, that's where the students come in.
35:22
So give us a glimpse, get a, give us a sense of where their
35:26
interests are and, and what you're trying to get them to look at.
35:30
Mohsen: Yeah, so actually, you know, every winter semester I'm, I actually
35:34
developed a course at the plant agriculture department at University of
35:37
Guelph, and the course is mostly about, you know, in intro to computational
35:41
biology and agricultural science.
35:43
So I'm trying to teach different s we call it like different.
35:47
Words like, you know, phenomic genomics, transcriptomics, proteomics, all
35:51
this kind of word, like big words.
35:54
And how we can integrate all of them through different AI and through different
35:59
algorithms and how we can, uh, find the best, like, you know, the actual, uh,
36:06
background behind any traits of interest that we are interested to work with.
36:10
So.
36:11
This is one of the course that I developed for the graduate students and also for
36:15
the undergrad, specifically for the second year undergraduate students.
36:19
I was just thinking, okay, how about letting students to make their hand
36:23
more dirty and dirty into the data?
36:26
So I develop bio data for people, plant, planet, and I'm going to teach it for
36:30
the first time in this coming fall.
36:33
I'm not sure that you know what will happen, but I'm really looking forward
36:36
to that and I'm thinking that, you know, it would be a good source for a
36:38
student to make them ready for the future courses that they are going to take.
36:42
Right?
36:42
So, so far I'm like, you know, last year I was able to teach, applied
36:48
Bioformatics and how we are using bioinformatic in agriculture.
36:52
So all of them, I found that, you know, students are very
36:56
much interested use trends.
37:00
Like they are interested to work with ai and every time they're telling
37:04
me, okay, Mosen, we love to work ai, how we are developing this ai,
37:08
how we are working with that ai.
37:10
And the first question that I'm asking them is why you wanted to work with ai.
37:14
Is it, do you think that you know AI is really right tools for you?
37:18
What type of data you have?
37:20
Do you think your data is big enough?
37:22
Or your data is large, or your data is streaming data or the complex data,
37:27
each of them has different meaning.
37:30
So don't get interested.
37:32
Don't get excited and just brag that, Hey, I'm working with ai.
37:36
Of course, working with AI is good, but have you had this kind of
37:42
like, you know, good understanding why you wanted to do that.
37:45
So this is something that I'm going to teach analytical thinking.
37:51
think before selecting the right or the like, you know, whatever algorithms,
37:55
whatever path you wanted to choose in your future, just think before that.
38:01
Don't just follow because it's trend.
38:04
Don't get excited of everything that comes new.
38:07
If you are seeing, okay, this is the huge potential, even, you know, the
38:11
reason just that's, that's interesting.
38:14
The reason that I started to work with machine learning and those ai,
38:18
like you know, many years ago was not because on that time it was not
38:22
trendy, I was just searching among all the literature and I found that,
38:26
okay, there may be a good use of these kind of algorithms in agriculture.
38:31
I can't test them.
38:33
So I started to
38:34
Jesse Hirsh: Not test them, and even in home,
38:36
Mohsen: that time no one buy it.
38:38
Right.
38:38
You know, they told me that.
38:39
Okay, yeah.
38:40
You are living in your dream and you are not an actual breeder.
38:44
I
38:44
Jesse Hirsh: I never gave.
38:45
Mohsen: give up.
38:46
Gave up because you know, I just wanted to work on that area and I did.
38:49
And now you are seeing that, okay, here is the real things right, and
38:53
we are working on everyday life.
38:55
So if I wanted to just only use whatever is getting trend,
38:59
I'm not going to be successful.
39:01
And this is something that I wanted to teach my students and I like,
39:06
you know, they are at the end of the semester, they are all getting
39:09
appreciated and said that, hey, right now we have a good understanding of
39:13
whatever data we have, or maybe we can use the simple statistical analysis.
39:18
we can get the body where we want it, right?
39:21
It's not just only using the fancy ai.
39:25
We can use a simple, having a good discussion and understand why and
39:31
what is the data and how we can use this data in a better way.
39:36
Jesse Hirsh: Okay, let me see if I can use a metaphor to set up my next
39:41
question, because one of the recurring themes of our conversation today, which I
39:45
think you, you just evoked again, is the idea that there's this learning curve.
39:50
And to be a good researcher, you wanna push yourself up that learning curve.
39:54
You, you wanna challenge yourself and to your point, not
39:58
be content to be in the trends.
40:00
To really try to go further and anticipate either your own curiosity or where the
40:05
world is headed, that's clearly what you're encouraging your students to do.
40:10
Where does industry fall in that learning curve?
40:14
Right?
40:14
In your interactions, not just with big industry, but even farmers,
40:19
even PE, agronomists, people who are curious about this stuff.
40:23
Where are they on that learning curve and, and how do you do what you do with the
40:27
students, which is encourage them to be courageous, encourage them to really try
40:33
to imagine where we need to be to make the most of this technology and these tools
40:39
Mohsen: Oh
40:40
Jesse Hirsh: I.
40:40
Mohsen: so you know what this is.
40:41
This is actually one of the things that I am working every day, and at
40:45
the same time, I'm trying to improve my day every day by any interaction that
40:50
I have with farmers, growers, industry partners, and also government bodies.
40:54
So each of them, you need to make sure that you have, you know, their own
40:59
Jesse Hirsh: Stack picture,
41:00
Mohsen: how to talk with them, right?
41:02
It's
41:02
Jesse Hirsh: it's
41:03
Mohsen: something that
41:04
Jesse Hirsh: that I can.
41:05
Mohsen: the rag models and some of the statistical analysis
41:08
behind everything to the farmers.
41:09
They all just saying, okay, what would be the most benefit of it?
41:13
And what I found is farmers are really, is real.
41:16
Uh, they are really appreciate something that I can just show them,
41:21
Hey, here is something that would work.
41:23
Right.
41:23
Test them and see if it works.
41:26
You can just, you guys can also dig into it and learn more about
41:30
it and we can work together.
41:32
And you know what, I'm proud to say that I have a very good
41:35
supporters in terms of the farmers.
41:37
I have Ontario bin Growers.
41:38
They are supporting me in different aspects of my programme.
41:42
And of the times they invited me to give a talk to actual, to their
41:46
a GM, to their research, day, but.
41:50
They are not asking me to talk about the actual bean seeds or anything.
41:55
Last time they asked me to talk about bean GPT.
41:59
Because they are also interested to see what is this being GPT look
42:03
like, how they can use this AI in their actual day-to-day work.
42:07
Jesse Hirsh: Right.
42:08
Mohsen: And it was last Friday that I was, that I was talking to a couple of
42:12
them and I told them that, yeah, here is the ai here is we are doing, and they
42:17
told me that they are advocating for AI in different committee on, on my behalf.
42:22
You know what, this is the interaction.
42:24
This is the relation that I really appreciate.
42:27
I really admire that and I've seen, I've seen such this kind of
42:32
openness in different places, but it depends on how you approach them.
42:38
Another reason, another example that I can give you about like some of the industry
42:42
partners that I'm working with them.
42:44
So they are actually appreciated ai, they are actually appreciated.
42:48
These kind of trends, things and everything.
42:52
to what extent, what, what is the benefits?
42:55
If you can show the real benefit to them, that's perfect.
42:58
If you couldn't prove it.
43:01
couldn't prove it.
43:02
Okay, so what's the, what's the point?
43:04
Right?
43:05
And this is the gap that
43:07
Jesse Hirsh: that.
43:07
Mohsen: I think it's in the, like, you know, research areas that we are
43:11
doing so many advanced technologies and advancing things, right?
43:15
But when we wanted to translate to the actual, to the applied settings.
43:20
We are sometimes like, you know, lagging behind.
43:22
So this is something that I am actually learning every day and
43:26
it's a learning curve for me.
43:27
And I'm also trying to, um, provide this kind of experience that I had, you
43:32
know, to my students and everyone who like to work as an industry partners,
43:37
like, you know, indu work in the industry or academia in the future.
43:42
also the last part is in this case is we are training, whoever
43:47
we are training right now.
43:49
They are going to build the future.
43:52
So if we are able to tell them, okay, here is the research and here is the way
43:57
that we are interacting, they can also realise, okay, this is the way that the
44:02
academia interact with the farmers, with the growers, with the industry partners.
44:07
Once they are, became, become, you know, a farmer, become a grower, become industry.
44:14
in the future.
44:15
They are realising this kind of interaction.
44:18
They are already this kind of like, you know, relation has
44:21
already been built, right?
44:23
So it can facilitate.
44:25
So whatever that we are doing is not only benefiting us for today, it's also for
44:30
the future and the future generation.
44:32
And this is something that I'm.
44:34
Jesse Hirsh: So l let, let me throw a relevant follow up at you.
44:37
And, and I say this only 'cause I, I've encountered this myself and I'm kind
44:41
of curious what your advice would be or, or what your approach would be.
44:45
But I think a lot of the farmers that you're describing are kind of
44:49
self-selected, curious, and on the one end, you're right, they want see the
44:54
tangible, they wanna see how it works.
44:57
But I, I think who we should acknowledge, 'cause they're
45:00
the people who don't come up.
45:02
Are those who are afraid because there are people in our society
45:06
for various different reasons who are kind of scared of ai.
45:11
I encounter that all the time.
45:13
I try to foster their curiosity.
45:14
I try to help them see past all the nonsense to look at it
45:18
as a tool that can help them.
45:21
But how do you approach that?
45:22
You know, how do you deal with people who, whether they're in the agricultural
45:26
sector or in your family, or people you just encounter on the street and they
45:31
know Mosson is a guy who's into ai, how, how do you address that kind of fear?
45:38
Because I, I think for some people it's like the obstacle to them learning all the
45:42
stuff that we're talking about that I, I think we both think is really exciting.
45:47
Mohsen: Oh, that's actually, this is, this is one of the most important
45:51
things that we are facing these days, to just make sure, like, you know.
45:56
It's at the same time we are certain, certain about some sort of things, and
46:00
at the same time, we are uncertain about some sort of things that happening.
46:04
So I can tell you an example.
46:06
I, I've, uh, so many people ask me the same question, will AI replace our job?
46:12
What do we need to do?
46:13
Like, you know, these ai uh, I, I can't rely, I can't trust ai how you are
46:18
like building everything on the ai.
46:20
Not everything.
46:21
Most of the things that you are working is, has been built, you know, in ai.
46:25
How you do that are, you are not afraid when you are developing
46:29
a co breeder ai co breather.
46:32
When you are not afraid that these co breather will in the future
46:37
is getting to an actual breather.
46:39
Breather, and they cannot replace your jaw.
46:42
I received these tonnes of questions and you know what?
46:46
Up to a couple of months ago, I had not a clear answer for them.
46:52
I was
46:53
Jesse Hirsh: I.
46:53
Mohsen: to say, okay, yeah, here's the ai.
46:55
Here's the AI would be good.
46:57
I don't know what will happen in the future, but if you have the good
47:00
idea, if you have the good, like, you know, working in this area, there
47:04
are always, you know, job for you.
47:06
There are always, you are not just AI is going to help you.
47:09
So I was just ask, answering these kind of things until at
47:14
one night, over the weekend just got bored, of the watching tv.
47:20
So I
47:20
Jesse Hirsh: If I.
47:20
Mohsen: to start back to the working and it, I re exactly remember that
47:25
it was like 11:00 AM It was somehow at the midnight asking Claude.
47:31
To develop an app that is currently exist, but adding these new informations
47:37
and these new techniques there.
47:39
I asked Claude that, Hey, Claude, can you develop.
47:43
ODM.
47:43
There, there, there is a app, like, call it web, ODM.
47:46
I don't want to go through the details, but this is for the, uh, stitching
47:50
all the drone images together to get the actual orthomosaic picture.
47:55
So I asked this, oh, like, you know, Claude, that can
47:58
you develop web ODM for me?
48:01
And Claude for the, at the first glance, responded, yes, here is the one.
48:06
So I check it and I found it.
48:08
No, it's not.
48:09
I replied
48:11
Jesse Hirsh: back.
48:11
Mohsen: not.
48:12
you do this again?
48:14
The same thing?
48:16
No, that's not, can you redo this?
48:18
Redo, redo, redo.
48:20
And it was around 5:00 AM after tonnes of back and forth.
48:25
I got so frustrated and I asked Claude, Hey Claude, I told
48:29
you to create this app for me.
48:31
Why you are doing this?
48:33
And you know what, what?
48:34
Claude responded back to me.
48:35
That was interesting.
48:37
I respond?
48:38
But I understand your frustration, but just to let you know, that web
48:42
ODM was built based on human, and it was based built for like, you know,
48:48
it's around 500,000 lines of code.
48:52
There I am AI and I'm only able to develop 4,000, 5,000 lines of code.
48:59
I'm not able to do that.
49:01
So you know what?
49:02
At 5:00 AM I was just thinking, okay, I got the answer.
49:08
Will AI replace our job?
49:10
It depends how many lines of code we are worth it.
49:16
If you are worth 5,000 lines of code, of course you can be replaced.
49:23
it's 500,000 lines of code with the novel idea, with tonnes of work behind it.
49:29
No, it's not going to happen.
49:31
And you are the one who are going to train ai.
49:34
You are the one who are going to just, you know, build ai.
49:39
So that's the answer I found that.
49:42
And it was like, you know, it cost me six hours, not atop like back and forth
49:47
with Claude, but finally I found the right answer to like, you know, respond.
49:52
Like anyone who are asking me right now, I have something to say.
49:56
Yeah, it totally depends on you.
49:58
I can't tell you that.
49:59
Will AI replace your job or not?
50:02
Check, see how many lines of code you are worth it.
50:06
Jesse Hirsh: Well, and, and the brilliance of that answer is that with
50:10
each research paper that you read, the lines of code in your software increases.
50:17
Every research paper you write exponentially increases the lines
50:22
of code in your software stack.
50:24
And this is where I will say to any farmers or drone operators listening,
50:29
if you don't know what web ODM is.
50:32
Give it a Google, because if you do have a drone, you could do a
50:36
lot of fun stuff with Web ODM.
50:39
We're digressing.
50:40
Uh, we're, we're just about out of time, Mosen, and the, one of the last
50:44
questions I ask our guests, this is usually the second last I ask, is
50:49
there anything that we haven't talked about today that we should talk about?
50:53
And this could be research that you're currently excited about, or
50:58
concerns or thoughts that you want.
51:00
Other leaders in the sector to be thinking about when it comes to these tools and
51:05
it comes to the potential of these tools.
51:08
Mohsen: Oh yeah, so you know what I appreciate.
51:10
Just, you know, we, we've covered so many different things and
51:13
I really enjoy talking to you.
51:15
Something that I just wanted to put emphasise on it is.
51:21
Whatever we are developing, whatever we are advancing, we should appreciate what
51:26
has been built for many years in the past.
51:29
We cannot replace our tradition.
51:32
We cannot replace whatever have been built.
51:35
Right?
51:37
I'm seeing that, you know, most of the times that I'm submitting any proposals
51:41
or developing new ideas and I'm just talking about it, people often, often
51:46
ask me that, Hey, Moss, are you.
51:48
Traditional breeder, or you are the new breeder or whatever
51:52
you wanted to just use.
51:54
You are not using any traditional things.
51:56
You are using like new and innovative tools.
51:59
And I wanted to say it's a mixture of both.
52:03
I have to respect traditional breeding.
52:05
Traditional breeding is something that I cannot replace it.
52:08
No one can replace it with any new technologies.
52:12
We can compliment whatever has been built for many years.
52:18
it's the science, it's not practical, it's not based on probability.
52:24
It's not so many.
52:25
It's, it's pure science.
52:27
And you know what we have in the definition of the plant breeding as the
52:31
art and science, and it's totally true.
52:34
I've just right now realised it with my own, like, you know, full,
52:38
like, you know, the point is.
52:40
We have to make a best decision our eye, by our feeling, and we have to have, be an
52:47
artist to develop and design a good plan.
52:50
At the same time, we need to follow science to see what's going
52:54
on on the biological background.
52:55
What is the biological background behind any traits, how this plan look like,
53:00
how this plan perform, get the DNA, other things This should be acknowledged
53:07
that plant breeding is actual science.
53:10
It's not the practical things that we are doing.
53:13
Right, for any plant breeder, our job is not finding the best.
53:19
Our job is to find real assets in everything that we are working.
53:25
Is, is, is something that I. trying to move toward it.
53:29
I'm trying to just realise even a little and tiny data that we are collecting
53:34
a small plant, that we are living in the field, what we can best deal
53:38
and do, you know, do from like, you know, how we can use of them, right?
53:42
So this is something that I wanted to emphasise more about it and just,
53:46
you know, let you know that, that, you know, this kind of breeding.
53:49
Yeah, like I can't, I can talk on behalf of all plant breeders and
53:53
I, and I know that, you know, they all would be appreciated that I'm
53:56
telling this, for every dollar that is spending in this area, it's around
54:03
35 to $40 we are receiving, like, you know, any government receiving back.
54:09
Right?
54:09
So it's, you are spending $1 and you are receiving 35 to $40 back.
54:16
So these supports need to be continued.
54:19
If you are stopping supporting anything like, you know, plant
54:22
breeders, it's not showing tomorrow.
54:25
It's showing in the next 10 years and that time, there is no way that
54:30
you can get it back and turning back.
54:33
Right.
54:33
I just wanted to give a like $1 to $35 to Doug Miller, the former
54:39
executive director of Canadian Soybean.
54:41
Uh, um.
54:43
CSGA, Canadian Society of, uh, CSGA.
54:48
It's, uh, anyway,
54:50
Jesse Hirsh: Canadian Soybean Growers Association.
54:54
Mohsen: No, it is.
54:55
Uh, is, uh, I can just search.
55:01
CSGA.
55:03
It's Canadian Seed Grower Association.
55:07
Jesse Hirsh: Right on.
55:07
Right on.
55:08
Mohsen: Is it Canadian Seed Grower Association?
55:10
Yeah.
55:10
Jesse Hirsh: In fact, you kind of previewed what perhaps we should talk
55:14
about the next time I have you on.
55:16
'cause we've alluded today the entire time to food security.
55:21
But due to my fault, we've spent a lot of time focusing on the technology
55:26
and the role technology plays.
55:28
But we can talk about the role that technology plays around food security.
55:33
To your point about the payback that comes from spending money
55:36
on researching plant breeding and researching in particular beans.
55:41
Um, on the last question, which again, you almost just gotta answered right there.
55:46
The last question I throw to guess is who do you look up to?
55:49
Who are the leaders that we should be listening to?
55:52
It's kind of the shout out section of the show, and it's meant to be spontaneous.
55:57
It's meant to catch you off guard in the sense, what's the first
56:00
name that comes to your head?
56:02
Mohsen: In the plant breeding area or in the computational biology or like,
56:07
Jesse Hirsh: Anywhere.
56:08
This is like the, this is like the first question.
56:10
What is the future?
56:10
This is the the last question.
56:13
Who do you look to for inspiration?
56:16
Mohsen: Oh, I'm just looking like, you know, the first name that is coming to
56:19
my mind is, Dr. Ricko is coming to my mind and I have, I have tonnes of, tonnes
56:25
of people who I really admire them and I just wanted, I just following their
56:29
work and everything, Dr. Seth Moray, I'm just, you know, following their
56:33
work yeah, there are tonnes I can't really, you know, tell you about it.
56:38
And it's not only breeders, they are also.
56:41
Some of the farmers, growers, like, you know, industry partners, they
56:44
are all people who are following.
56:46
Yeah,
56:47
Jesse Hirsh: And that's why I throw it as the last question 'cause it's not
56:50
like it's, you know, the Oscars or the Academy Awards where you can thank all
56:54
the people who helped make the movie.
56:56
This is about one or two names and you did it spectacularly most.
57:00
And speaking of which, this episode, like many of our episodes, has completely
57:06
blown my mind, partly because of the enthusiasm you bring to your research.
57:12
But also 'cause I really feel you make this stuff accessible.
57:15
Like you really help, to your point, farmers have kind of forced you to talk
57:20
about this stuff in a way that that gets to the point, that speaks to kinda what's
57:25
at stake and what the opportunity is.
57:28
So.
57:29
Thank you very much.
57:30
I mean, I, I really feel that this is, uh, the start, uh, of some conversations
57:35
between us to really help people see what you see, which is the potential
57:40
for this technology to really not just revolutionise agriculture, but address,
57:45
uh, food security at a global scale.
57:48
Thank you very much.
57:50
Mohsen: Oh.
57:51
Thank you so much for having me.
57:52
Just the point is, you know, I'm moving toward it to make everything
57:57
accessible, to make it everything, like, you know, facilitated for learning
58:00
and I'm at the same time learning.
58:03
And you know what?
58:05
Something that I wanted to say at the end is none of the things that I'm
58:10
right now doing would've been possible without a great support my mentors, Dr.
58:15
Isman Chens, you know, and also like, you know, uh, some of the
58:19
supporters that I have, like the.
58:21
Ontario being growers.
58:23
Right.
58:23
So, and that I just, you know, support, I received the support and crich those
58:29
like, you know, supporters are just very like, you know, helpful to build up my
58:33
research programme and they are trusting me on just doing all these kind of things.
58:38
I would, I, I would like to also thanks them at the end as well.
58:41
Jesse Hirsh: Right on.
58:42
Mohsen: for having me and I'm really looking forward to having
58:44
another conversation with you about more exciting stuff.
58:48
Right.
58:49
Jesse Hirsh: Right on.
58:56
I hope you enjoyed that half as much as Mosin and I did.
59:00
Uh, it's no exaggeration to say that sometimes talking about AI leads
59:05
to a kind of time blindness where you don't even realise how long,
59:09
uh, uh, how much time has passed.
59:13
Uh, while I do make an effort to keep our episodes on time.
59:17
Clearly Mosen and I are gonna have to continue this conversation if only
59:22
to explore the kind of Venn diagram where traditional agriculture and
59:27
some of these new practises overlap.
59:30
Because what I found so affirming about Moss's Worldview is it's not an either or.
59:37
It's not about embracing the future at the expense of the past.
59:41
Rather, it's about using the future to reinforce our values
59:46
from the past, to use data and intuition together and in concert.
59:52
And that's why accessibility matters.
59:55
That's why when it comes to talking about technology on the farm, it's not about.
59:59
Companies, it's not about experts, it's about farmers playing with these tools,
1:00:04
seeing how they can bend the tools to their practises rather than expecting
1:00:09
their practises to bend to the tools.
1:00:12
Now before we close, I, I do wanna point out that we've got
1:00:16
an exciting new pilot project.
1:00:18
Called Commons do the future, her.ca.
1:00:22
We're currently solicitating your views about food security, and we
1:00:27
did kind of touch upon that today in terms of AI and food security.
1:00:31
But we are gonna be expanding the topics that we are focusing on, uh, when it
1:00:36
comes to employing the commons, one of which is gonna be the 2050 process itself.
1:00:42
What do you see in the future?
1:00:44
But another is gonna be about AI and agriculture, which includes ethics, which
1:00:48
includes governance, which quite frankly includes any views you may have on ai.
1:00:54
So if you are still listening, that means you enjoy this episode enough to at least
1:00:59
share it with your friends, but also to go check out our website and see what
1:01:03
we've going on, some of the features we've got, so that moving forward.
1:01:08
You can see yourself as part of the herd, even when I press the intro button and
1:01:14
instead I want the outro button so I can evoke that kind of 1970s television vibe
1:01:22
that I'm currently using to set the tone, the motif, the culture of the future herd.
1:01:30
If you have any questions about the podcast, about the process.
1:01:34
About the age agentic software we're billing to facilitate
1:01:37
podcast production, drop us a line.
1:01:41
Uh, hello@thefutureheard.ca or complain or cove about us on social media.
1:01:50
Uh, what did they used to say?
1:01:51
Good news, bad news.
1:01:52
It's all news.
1:01:53
Good attention.
1:01:54
Bad attention.
1:01:55
It's all attention.
1:01:57
And if there's anything we want, it's yours.
1:02:00
I'm Cheezy Hirsch.
1:02:04
See ya.