March 17, 2025 • 25 mins
What if AI could tell you the best time to cut hay or monitor your livestock 24/7? In this episode of Just Say Hay: The Podcast, Jon explores how artificial intelligence is transforming small farms—not just for big ag, but for farmers like you. From AI-powered weather predictions to computer vision tools that identify weeds in your field, we break down what’s real, what’s hype, and where the biggest risks lie. Plus, John sits down with a special “guest” to demonstrate AI in action—can it really hold a conversation? Tune in for an insightful discussion on how farmers can embrace AI without getting lost in the tech.
🔹 How AI is already helping small farms
🔹 The biggest myths about AI in agriculture
🔹 Risks, biases, and the future of AI-driven decision-making
🔹 Why staying informed about AI policies is crucial for farmers
Don’t miss this deep dive into the rise of AI in everyday farming!
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Speaker 1 (00:00):
Welcome to Just Say hey.
The podcast podcast where wetalk about the things that
matter to small farms, and todayis no different.
You know, if you could havetold your
great-great-grandparents thatthere would come a time in life
where you would have a box thatyou'd carry with you everywhere
(00:20):
you went, that you'd carry withyou everywhere you went, that
not only allowed you tocommunicate with any place in
the world, but also containedthe entire database of human
knowledge, they would havelooked at you like you were
(00:43):
insane.
They would have thought thiswould have been more
revolutionary than the fact thatwe fly on airplanes at faster
than the speed of sound or thatwe have landed on the moon.
And I think we're in a time ofanother technological revolution
that, as small farmers, wereally need to be paying
(01:10):
attention to.
And, whether we like it or not,ai is here to stay.
It's not going anywhere, butit's not just for big tech
companies anymore.
We need, as small farmers, weneed every advantage we can get
(01:31):
to make our businessesprofitable, to keep our farms
running, to be able to make gooddecisions, and I think we are
at the point, finally, that AIis giving us some tools that are
actually beneficial for smallfarmers.
You hear a lot about AI for bigfarmers.
I want to talk about what'sreal, what's hype, where the
(01:52):
dangers are, what are the thingsthat we need to pay attention
to as we start into this new ageof AI.
And then also right after theintro here I've got a really
special guest that'll be kind ofcool to talk to and ask some
questions.
Right after the intro here I'vegot a really special guest
that'll be kind of cool to talkto and ask some questions.
But before we get there, if youlike this podcast and you think
I'm giving you some goodinformation, let me know what I
(02:13):
can help you out, with, whattopics you'd like me to cover,
and also share this with yourfriends and family.
It really helps out.
I appreciate it.
Welcome to Just Say hey.
The podcast where we talk aboutwhat matters to small farms,
whether it's business, marketing, agronomy, equipment, livestock
.
If it matters to small farms,we'll probably talk about it
here.
So let's get into it.
All right, hey, bot welcome tothe show.
Speaker 2 (02:36):
Thanks, john, it's great to be here.
What's our topic for today?
Speaker 1 (02:47):
So we're talking about AI and small farms and I
was going to ask if you couldtell us in your mind what is a
good definition of AI?
Speaker 2 (02:50):
Sure, AI, or artificial intelligence, is
essentially technology thatallows machines to mimic human
intelligence.
It can learn from data,recognize patterns and even make
decisions.
In small farms, AI can helpwith tasks like monitoring crops
, predicting yields andoptimizing resource use.
Speaker 1 (03:07):
It sort of sounds futuristic, almost like a sci-fi
movie, but what are some simple, real-world ways that AI is
already helping small farms?
Speaker 2 (03:16):
Absolutely, John.
Ai is being used in small farmsin some really practical ways.
For example, AI-powered sensorscan monitor soil health and
moisture levels, which helpsfarmers water their crops more
efficiently.
Drones equipped with AI cansurvey fields to check on crop
health and detect pests early.
There are also AI-driven toolsthat can predict the best times
(03:38):
for planting and harvestingbased on weather patterns and
soil conditions.
It's all about making farmingsmarter and more sustainable.
Speaker 1 (03:49):
I know a lot of farmers rely on their gut and
instinct and experience to makedecisions, but can AI really
compete with that?
That's a great point.
Speaker 2 (03:53):
AI isn't about replacing a farmer's intuition
and experience.
It's more like a tool tocomplement and enhance them.
Farmers still make the finaldecisions, but AI can provide
data-driven insights that mightnot be immediately obvious.
It's about blending technologywith traditional knowledge to
make farming even more effective.
Speaker 1 (04:12):
So how does it help with things like predicting
weather or knowing when to cutmy hay?
Speaker 2 (04:16):
AI can analyze vast amounts of weather data to
predict trends more accuratelythan traditional methods.
It can tell you the optimaltime to cut your hay by
considering factors likehumidity, temperature and
upcoming weather conditions.
This helps ensure you get thebest quality hay and avoid
unexpected weather issues.
Speaker 1 (04:35):
So what's one AI tool that a small farm could use
right now with no learning curve?
Speaker 2 (04:41):
A simple tool would be an AI-powered weather
forecasting app.
Many of these apps areuser-friendly and offer precise,
tailored weather predictionsfor your farm, helping you make
informed decisions without asteep learning curve.
Speaker 1 (04:54):
So what is the biggest myth or misunderstanding
about AI in farming right now?
Speaker 2 (05:00):
The biggest myth is that AI is too complicated or
only for large-scale operations.
In reality, many AI tools aredesigned to be accessible and
beneficial even for small farms.
Speaker 1 (05:14):
It's about enhancing existing practices, not
replacing them.
So farming's changed a lot overthe last 50 years.
If AI keeps advancing, what'sone way you think small farms
might look different in, say, 10years from now?
Speaker 2 (05:23):
In 10 years, small farms might be more
tech-integrated.
Using AI for precisionagriculture, we could see
widespread use of autonomousmachinery, drones for crop
monitoring and advanced dataanalytics to optimize every
aspect of farming.
This could mean more efficientresource use, higher yields and
even greater sustainability.
Speaker 1 (05:43):
Can you give me a limerick about a hay farmer in
the rain?
Speaker 2 (05:47):
Sure, here's a quick limerick.
There once was a farmer namedRay whose hay fields were soaked
every May.
With AI's great aid, he knewwhen to cut hay, and now he
makes bales come what may.
Speaker 1 (05:59):
All right, thank you.
Have a great day you too, john,take care.
Well, in case you didn't realizewhat was going on there, I had
the questions that I wanted toask, but there was nothing that
had been pre-programmed.
It was just a conversation andthe AI was actually hearing what
I said, figuring out what wordsI was using, what question I
(06:20):
was asking, and then responding,thinking like a person.
It just blows me away how goodit is.
I remember, oh, back in the mid1990s, I was involved in a tech
startup that was doing what wecall concatenated speech, and it
(06:42):
was the first beginnings ofwhat became a very famous AI
program and and it's amazing tome how far it has come in not
only the sound of the voice andthat's not one of the better
voices that can be used it'sjust what was there.
But it is amazing that it canunderstand now and figure out
(07:03):
what you're saying in justsimple English.
To really kind of understand,there are basically three main
types of AI, because there's notat this point, there's not one
(07:25):
AI to rule them all.
It's sort of there are.
You use artificial intelligenceto perform tasks or accomplish
things.
So what we call core AI is likewhat we just talked to.
It was a large language modelAI, but you also have generative
AI, which is you may have seenon Canva or some of these other
programs.
You can have it make a picturefor you.
You write in a text prompt andit makes a picture.
(07:45):
So you know, those are probablythe most popular.
But where I think for farming,where it really gets interesting
is in functional AI, where AIis trained to do predictive
analysis, have computer visionor autonomy, where it's learning
and understanding itsenvironment and performing a
(08:07):
task based on feedback from theenvironment.
You know, and predictive isthings like weather, livestock,
you know things like that.
Where computer vision is.
I use computer vision right nowand it's a simple app.
I think it's called picture this.
I'll be standing out in thefield and I'll see a weed and I
(08:28):
don't know, I may not know whatthat plant is, and I just walk
over there, this thing, I openit up, I load it on my take a
picture of it with my camera onmy phone and this program goes
in and identifies it for me sothat when I call my spray guys I
say, hey, I've got a field fullof this.
What can we do to kill mare'stail or lamb's tail or amaranth
(08:51):
or spiny amaranth or you knowany one of these weeds that we
see.
Being a first-generation farmer, I didn't grow up looking at
these weeds, so I have to learn,and if there's not somebody
there to ask, I literally take apicture of it and this program
will tell me what plant is in myfield, and so I know how to
deal with it.
Is this a harmful plant that Ineed to really get rid of this,
(09:14):
or is this just a, you know, alate summer weed that will die
out and has no health effects onthe?
Speaker 2 (09:19):
animals.
I'm feeding.
Speaker 1 (09:21):
So I think you know we're using this more and more
and I'll just tell you.
There's a last type of AI, justcalled learning-based, where
it's reinforced learning.
I think the Tesla cars use this.
Where it drives, it drivesuntil it makes a mistake.
Where it, when it makes amistake, it learns and doesn't
do it again.
So it's a reinforced learningmodel.
There is so many things goingon in AI and it's going to start
(09:44):
moving even faster.
Like computer programming, mostprogrammers are using AI right
now to generate the code insteadof spending a thousand hours.
I saw a guy the other day thatcreated a complete iPhone app in
30 minutes.
In agriculture, you're seeingthe bigger farms.
(10:06):
This isn't quite the smallfarms yet.
It's not out of the realm forsmall farms, but for the most
part it's the bigger farms andthat's crop and soil monitoring,
where you have sensors orsatellite data and AI is looking
at this satellite data or thesesensors and giving you
recommendations or timings orthings like that.
Where I think we're using AI insmall farms is weather.
(10:27):
Now we use a service called BAMWeather and they're fantastic
and I'm sure they're using thisin some of their predictive
models, but they still are humanbeings going in and looking at
this and they are fantastic.
You also see it in livestockhealth management.
There's a company calledBreeder.
I think is, yeah, breeder,b-r-e-e-d-r, I think is the name
(10:52):
of the company, and they do inbeef herd management.
You put a sensor on your cowand it does temperature, pulse,
movement.
So it understands, it learns.
This program learns how thatcow moves.
It learns their temperatures.
There you know the how theirtemperature fluctuate,
fluctuates during the day,fluctuates during the day.
(11:17):
And then you know whensomething comes out of the
normal.
That cow gets a temperature orit stops moving or any one of a
number of factors.
It says hey, sends a message tothe farm, said hey, you need to
go check number 387B, she's notmoving, and so you know to go
right out there and do.
It works 24 hours a day.
I think the precision side wetalked about it in, you know,
(11:38):
kind of early on the precisionside is really interesting.
I mean the whole concept of thesee-in spray is just amazing.
I've seen a demo video of thesea and spray and the speed that
that machine is moving over thefield and making the decisions
(12:00):
to use or not use chemical basedon the identification of a
plant.
That's unbelievable to me.
And then, finally, for smallfarms.
I think there's a lot ofapplications out there that use
artificial intelligence that canhelp me.
I use it every day.
(12:20):
But it can use artificialintelligence for things like in
your business, whether it'sfinancial, whether it's
marketing, whether it's.
You know, there are things thatyou can use, even if it's just
to brainstorm ideas.
But companies that you may use,like QuickBooks or, you know,
facebook, they're usingartificial intelligence to help
drive better results forbusiness, and so it's something
(12:43):
we should keep an eye on.
And I'll say this because, youknow, I know I've kind of gone
through a lot of this prettyquick, but before we get into a
couple other things here, I'm abig fan of history.
I am, I love history.
I love reading books from theearly part of American history,
(13:05):
whether it's thepre-revolutionary war or the
settling of the Old West.
I've always been a fan of that.
And there's an author that I, I, everybody knows who he is
louis lamore um.
Have you ever seen john wayne'shondo?
That's a louis lamore storyhe's written.
I mean, I've read every one ofhis books, uh, but one of my.
(13:27):
You know, some of my favoritebooks are books like um, the
lonesome gods or the comstockLoad or Last of the Breed is one
of my favorites, every singleone of his books.
The land is part of thechallenge.
It's almost like it's acharacter in the book because it
(13:49):
determined a lot about thestory.
Determined a lot about thestory.
I mean, for example, if youwere coming over in the you know
the early 19th century, like1820s, 1830s, and you were
planning to go out west, youknow, man, it's a six to nine
month journey.
(14:10):
When you got to Missouri, youbetter have a good wagon, you
better have a team, you betterhave a cow for milk, you better
have enough beans and bacon tolast months.
When you got going over theplains, if you went the northern
route, if you went over theplains, you had to leave at a
certain time of year because youwere going to run into winter
weather.
Going across the Rockies, theRockies, you had to go across
(14:40):
the desert.
I mean, and this was such achallenge, and we are in this
era of AI, we are in this, Ithink this paradigm change that
there is so much data and somuch information out there that
we have to plan to conquer it.
We have to conquer thisinformation to be better at what
we do, and that takes planningand it takes understanding.
(15:03):
I mean guys would learn for ayear, would study for a year and
plan for a year before theymade the crossing to get out to
California.
I mean it was a big deal and Ithink if you're farming now you
need to be planning what you cando to mitigate risk, because if
you farm you know it's a gambleevery year and understanding
(15:25):
how we can use these tools tomitigate our risk, to make the
passage safer.
I mean the planning, theunderstanding, and I see these
parallels in you know,technological changes.
I mean imagine going from youknow where you had to cross the
plains with a horse and a wagonto where you can drive in your
(15:48):
air conditioner, yourtemperature controlled car at 80
miles an hour and cross fromcoast to coast in just a matter
of days To where now you can.
Instead of sending letters topeople you haven't seen in years
, you can now pick up the phoneand talk to them almost
instantly, anywhere they are Tonow understanding massive
(16:12):
amounts of data Imagine weatheris one of the most complex data
sets that there is and we havetools now that allow us to
analyze that for our specificlocation.
And as we understand thosethings, what does that do for us
?
It allows us to make betterdecisions.
(16:33):
It allows us to make betterdecisions.
It allows us to make moreinformed choices.
Farming is still up to us and Imean if we went in there and
asked here, we'll do it rightnow, just to We'll ask this
question.
Hey, hay bot, I've got aquestion for you.
Speaker 2 (16:53):
Sure thing, John.
What's your question?
Speaker 1 (16:55):
In the middle of winter.
Would you get outside thetractor for me and take net wrap
off of my hay?
I hate that job.
Speaker 2 (17:02):
I can imagine that's a tough job, especially in the
cold, but I'm here to keep youcompany and offer any tips if
you need them.
I'm here to keep you companyand offer any tips if you need
them.
Speaker 1 (17:12):
I think those kind of things that we have to do as
farmers are they're always goingto be the things we have to do
but when we can make betterdecisions on livestock, when we
can have somebody monitor ourstock 24 hours a day and know
when we have to be out there tocheck calving, for example, I
mean, imagine being, you know, acow-calf operator.
(17:34):
You got 250, 350 mamas andyou're going into calving season
and you sleep perfectly sound.
You're asleep at night until asensor tells you that that
mama's going into labor.
Well, you better get up and getout there, because you know it
doesn't take long for a cow.
If that cow prolapses, oranything like that, you want to
(17:55):
be out there, but you don't wantto waste an entire night if you
don't have to, because there'sother things that you have to do
.
So I think there are times whenwe have to.
You know, look at the future asnot this big, scary thing, but
as how can it help us do thejobs we currently do better Now?
(18:17):
Are there risks with AI?
Are there things that we shouldbe afraid of?
Yes, and I think it's importantfor us to stay abreast of
policies regarding AI, imaginethis that you are using company
(18:41):
A we won't name any companies,but imagine you're using a
company's services to monitoryour crops and it sees a soil
deficiency because you havesensors.
So this program, this AI, knowsthat you have a soil deficiency
and it needs to recommendfertilizer.
Well, because of who owns thatAI and who's in control, and
(19:08):
because it has your data who'sin control and you know, because
of it has your data it can nowrecommend fertilizer.
That may or may not be the bestapplication, but it's owned by
the company, so that AI isgiving you what you think may be
the best information, but ithas.
It is programmed to haveloyalty to the company, to
(19:29):
recommend a company product or aprescription from that company,
and I think that's really,really important for us to
understand those relationshipsand I hope that's where
regulation you know withcompanies, because we don't know
.
There's no way to stay on topof that.
There has to be some way, andif you listen to this podcast,
(19:49):
you know I hate governmentregulations.
I hate them.
I think there are a few thingsthat the government needs to do,
because it can do it betterthan anybody else, but there's
only a few of them.
That's it, just a few of them.
But I think in AI there needsto be some sort of oversight,
(20:10):
whether it's governmental,whether it's private, that tells
us what loyalties that AI isgenerating that information for.
Again, I mean, their fertilizermight be $400 a ton, whereas
you can go down the road and buythe same, a similar fertilizer
that may be better for your soil, for $50 a ton.
(20:31):
Those are the sort of thingsthat we have to worry about.
I think the other big thing isdata ownership.
I really believe that you me,everybody, we should own our own
data.
We should own our own data andif we don't, we should make sure
(20:52):
that we, that it does not thatthat data ownership if it goes
away, if that data goes away, itdoes not impact our business.
So you know, I think there'ssome some issues with data
ownership, with becomingdependent on big tech or big ag.
I know we use John DeereOperations Center.
(21:13):
I mean it's an okay program.
I think they've.
You know it's going through agrowing phase again.
Is it perfect?
No, if you do everything inthere now, you're tied to John
Deere.
Now do you own your data?
I don't know.
We got to go read the fineprint on that.
There's nothing I do in JohnDeere that I couldn't recreate
(21:33):
in a couple hours somewhere else.
I think those are really thethree main issues that I worry
about Data ownership dependence,becoming dependent on one
technology or one company, andthen the bias and misinformation
.
You know that's a big one forme If you listen to several
podcasts.
(21:54):
I've talked about media biasand information bias, and I
think AI if it's not, if we'reusing a data set from a company
that we may not know the fullownership of this AI could be
biased towards that as company'sproducts and recommend those
things to us even though theymay not be, you know, the best
(22:15):
solution you know.
So, kind of to wrap up, I'djust like to say I don't think
we need to be afraid of AI.
I really don't.
I mean, we've all seen theTerminator.
I don't think that AI is goingto rise up and try to take over
humanity, and that's not what Iworry about.
What I worry about is greedCompanies using, you know, using
(22:39):
the AI tech to makerecommendations to us without
giving, without us having accessto all of our information.
Again, soil fertilizerrecommendations you know medical
.
Imagine that in medical.
Again, soil fertilizerrecommendations.
You know medical.
Imagine that in medical.
You know AI in medicine isgoing to be huge.
I mean there are going to be inthe next 10 years.
There are going to be hugerevolutions in medicine.
(23:02):
I would not be surprised in 20years to see a cure to cancer.
And you know you may think I'mjoking, I'm not.
I think that what would take ahuman being years, a doctor, a
PhD in data science years tostudy could be done by an AI
(23:26):
minutes or hours.
I think these are the thingswhere it really has the ability
to be a great help to humanity.
What I'm concerned about is thenature of man and woman.
I don't want to bediscriminatory, man and woman
but the nature of man to biasthe outcome to their benefit.
(23:50):
To bias the outcome to theirbenefit.
So when a medical AI recommendsmedication for you, are they
recommending a certain company'smedication or are they
recommending what's best for you?
Where is the loyalty of thatdata?
Is that data loyal to you anddoing what's best for you, or
loyal to the company and doingwhat's best for the company?
(24:11):
So you know, those are thingsto think about.
I think this is a time to beexcited about what's coming.
I really do and I think youknow you've heard me talk about
it before.
In chaos, there's opportunityand as small farms, I think
there are places we can be usingAI right now and using it
effectively.
It's not expensive.
(24:32):
Get in there and start learningit.
But we should be payingattention to policy, because any
policy that's coming out aboutAI regulations, especially when
it comes to health care, but inall forms of business that there
has to be some oversight,because it can get really bad
(24:54):
for us really quickly if wedon't watch it.
And with that, have a wonderfulday, good luck and God bless.
Welcome to Just Say hey.
The podcast podcast where wetalk about the things that
matter to small farms, and todayis no different.
You know, if you could havetold your
great-great-grandparents thatthere would come a time in life
where you would have a box thatyou'd carry with you everywhere
(00:20):
you went, that you'd carry withyou everywhere you went, that
not only allowed you tocommunicate with any place in
the world, but also containedthe entire database of human
knowledge, they would havelooked at you like you were
(00:43):
insane.
They would have thought thiswould have been more
revolutionary than the fact thatwe fly on airplanes at faster
than the speed of sound or thatwe have landed on the moon.
And I think we're in a time ofanother technological revolution
that, as small farmers, wereally need to be paying
(01:10):
attention to.
And, whether we like it or not,ai is here to stay.
It's not going anywhere, butit's not just for big tech
companies anymore.
We need, as small farmers, weneed every advantage we can get
(01:31):
to make our businessesprofitable, to keep our farms
running, to be able to make gooddecisions, and I think we are
at the point, finally, that AIis giving us some tools that are
actually beneficial for smallfarmers.
You hear a lot about AI for bigfarmers.
I want to talk about what'sreal, what's hype, where the
(01:52):
dangers are, what are the thingsthat we need to pay attention
to as we start into this new ageof AI.
And then also right after theintro here I've got a really
special guest that'll be kind ofcool to talk to and ask some
questions.
Right after the intro here I'vegot a really special guest
that'll be kind of cool to talkto and ask some questions.
But before we get there, if youlike this podcast and you think
I'm giving you some goodinformation, let me know what I
(02:13):
can help you out, with, whattopics you'd like me to cover,
and also share this with yourfriends and family.
It really helps out.
I appreciate it.
Welcome to Just Say hey.
The podcast where we talk aboutwhat matters to small farms,
whether it's business, marketing, agronomy, equipment, livestock
.
If it matters to small farms,we'll probably talk about it
here.
So let's get into it.
All right, hey, bot welcome tothe show.
Speaker 2 (02:36):
Thanks, john, it's great to be here.
What's our topic for today?
Speaker 1 (02:47):
So we're talking about AI and small farms and I
was going to ask if you couldtell us in your mind what is a
good definition of AI?
Speaker 2 (02:50):
Sure, AI, or artificial intelligence, is
essentially technology thatallows machines to mimic human
intelligence.
It can learn from data,recognize patterns and even make
decisions.
In small farms, AI can helpwith tasks like monitoring crops
, predicting yields andoptimizing resource use.
Speaker 1 (03:07):
It sort of sounds futuristic, almost like a sci-fi
movie, but what are some simple, real-world ways that AI is
already helping small farms?
Speaker 2 (03:16):
Absolutely, John.
Ai is being used in small farmsin some really practical ways.
For example, AI-powered sensorscan monitor soil health and
moisture levels, which helpsfarmers water their crops more
efficiently.
Drones equipped with AI cansurvey fields to check on crop
health and detect pests early.
There are also AI-driven toolsthat can predict the best times
(03:38):
for planting and harvestingbased on weather patterns and
soil conditions.
It's all about making farmingsmarter and more sustainable.
Speaker 1 (03:49):
I know a lot of farmers rely on their gut and
instinct and experience to makedecisions, but can AI really
compete with that?
That's a great point.
Speaker 2 (03:53):
AI isn't about replacing a farmer's intuition
and experience.
It's more like a tool tocomplement and enhance them.
Farmers still make the finaldecisions, but AI can provide
data-driven insights that mightnot be immediately obvious.
It's about blending technologywith traditional knowledge to
make farming even more effective.
Speaker 1 (04:12):
So how does it help with things like predicting
weather or knowing when to cutmy hay?
Speaker 2 (04:16):
AI can analyze vast amounts of weather data to
predict trends more accuratelythan traditional methods.
It can tell you the optimaltime to cut your hay by
considering factors likehumidity, temperature and
upcoming weather conditions.
This helps ensure you get thebest quality hay and avoid
unexpected weather issues.
Speaker 1 (04:35):
So what's one AI tool that a small farm could use
right now with no learning curve?
Speaker 2 (04:41):
A simple tool would be an AI-powered weather
forecasting app.
Many of these apps areuser-friendly and offer precise,
tailored weather predictionsfor your farm, helping you make
informed decisions without asteep learning curve.
Speaker 1 (04:54):
So what is the biggest myth or misunderstanding
about AI in farming right now?
Speaker 2 (05:00):
The biggest myth is that AI is too complicated or
only for large-scale operations.
In reality, many AI tools aredesigned to be accessible and
beneficial even for small farms.
Speaker 1 (05:14):
It's about enhancing existing practices, not
replacing them.
So farming's changed a lot overthe last 50 years.
If AI keeps advancing, what'sone way you think small farms
might look different in, say, 10years from now?
Speaker 2 (05:23):
In 10 years, small farms might be more
tech-integrated.
Using AI for precisionagriculture, we could see
widespread use of autonomousmachinery, drones for crop
monitoring and advanced dataanalytics to optimize every
aspect of farming.
This could mean more efficientresource use, higher yields and
even greater sustainability.
Speaker 1 (05:43):
Can you give me a limerick about a hay farmer in
the rain?
Speaker 2 (05:47):
Sure, here's a quick limerick.
There once was a farmer namedRay whose hay fields were soaked
every May.
With AI's great aid, he knewwhen to cut hay, and now he
makes bales come what may.
Speaker 1 (05:59):
All right, thank you.
Have a great day you too, john,take care.
Well, in case you didn't realizewhat was going on there, I had
the questions that I wanted toask, but there was nothing that
had been pre-programmed.
It was just a conversation andthe AI was actually hearing what
I said, figuring out what wordsI was using, what question I
(06:20):
was asking, and then responding,thinking like a person.
It just blows me away how goodit is.
I remember, oh, back in the mid1990s, I was involved in a tech
startup that was doing what wecall concatenated speech, and it
(06:42):
was the first beginnings ofwhat became a very famous AI
program and and it's amazing tome how far it has come in not
only the sound of the voice andthat's not one of the better
voices that can be used it'sjust what was there.
But it is amazing that it canunderstand now and figure out
(07:03):
what you're saying in justsimple English.
To really kind of understand,there are basically three main
types of AI, because there's notat this point, there's not one
(07:25):
AI to rule them all.
It's sort of there are.
You use artificial intelligenceto perform tasks or accomplish
things.
So what we call core AI is likewhat we just talked to.
It was a large language modelAI, but you also have generative
AI, which is you may have seenon Canva or some of these other
programs.
You can have it make a picturefor you.
You write in a text prompt andit makes a picture.
(07:45):
So you know, those are probablythe most popular.
But where I think for farming,where it really gets interesting
is in functional AI, where AIis trained to do predictive
analysis, have computer visionor autonomy, where it's learning
and understanding itsenvironment and performing a
(08:07):
task based on feedback from theenvironment.
You know, and predictive isthings like weather, livestock,
you know things like that.
Where computer vision is.
I use computer vision right nowand it's a simple app.
I think it's called picture this.
I'll be standing out in thefield and I'll see a weed and I
(08:28):
don't know, I may not know whatthat plant is, and I just walk
over there, this thing, I openit up, I load it on my take a
picture of it with my camera onmy phone and this program goes
in and identifies it for me sothat when I call my spray guys I
say, hey, I've got a field fullof this.
What can we do to kill mare'stail or lamb's tail or amaranth
(08:51):
or spiny amaranth or you knowany one of these weeds that we
see.
Being a first-generation farmer, I didn't grow up looking at
these weeds, so I have to learn,and if there's not somebody
there to ask, I literally take apicture of it and this program
will tell me what plant is in myfield, and so I know how to
deal with it.
Is this a harmful plant that Ineed to really get rid of this,
(09:14):
or is this just a, you know, alate summer weed that will die
out and has no health effects onthe?
Speaker 2 (09:19):
animals.
I'm feeding.
Speaker 1 (09:21):
So I think you know we're using this more and more
and I'll just tell you.
There's a last type of AI, justcalled learning-based, where
it's reinforced learning.
I think the Tesla cars use this.
Where it drives, it drivesuntil it makes a mistake.
Where it, when it makes amistake, it learns and doesn't
do it again.
So it's a reinforced learningmodel.
There is so many things goingon in AI and it's going to start
(09:44):
moving even faster.
Like computer programming, mostprogrammers are using AI right
now to generate the code insteadof spending a thousand hours.
I saw a guy the other day thatcreated a complete iPhone app in
30 minutes.
In agriculture, you're seeingthe bigger farms.
(10:06):
This isn't quite the smallfarms yet.
It's not out of the realm forsmall farms, but for the most
part it's the bigger farms andthat's crop and soil monitoring,
where you have sensors orsatellite data and AI is looking
at this satellite data or thesesensors and giving you
recommendations or timings orthings like that.
Where I think we're using AI insmall farms is weather.
(10:27):
Now we use a service called BAMWeather and they're fantastic
and I'm sure they're using thisin some of their predictive
models, but they still are humanbeings going in and looking at
this and they are fantastic.
You also see it in livestockhealth management.
There's a company calledBreeder.
I think is, yeah, breeder,b-r-e-e-d-r, I think is the name
(10:52):
of the company, and they do inbeef herd management.
You put a sensor on your cowand it does temperature, pulse,
movement.
So it understands, it learns.
This program learns how thatcow moves.
It learns their temperatures.
There you know the how theirtemperature fluctuate,
fluctuates during the day,fluctuates during the day.
(11:17):
And then you know whensomething comes out of the
normal.
That cow gets a temperature orit stops moving or any one of a
number of factors.
It says hey, sends a message tothe farm, said hey, you need to
go check number 387B, she's notmoving, and so you know to go
right out there and do.
It works 24 hours a day.
I think the precision side wetalked about it in, you know,
(11:38):
kind of early on the precisionside is really interesting.
I mean the whole concept of thesee-in spray is just amazing.
I've seen a demo video of thesea and spray and the speed that
that machine is moving over thefield and making the decisions
(12:00):
to use or not use chemical basedon the identification of a
plant.
That's unbelievable to me.
And then, finally, for smallfarms.
I think there's a lot ofapplications out there that use
artificial intelligence that canhelp me.
I use it every day.
(12:20):
But it can use artificialintelligence for things like in
your business, whether it'sfinancial, whether it's
marketing, whether it's.
You know, there are things thatyou can use, even if it's just
to brainstorm ideas.
But companies that you may use,like QuickBooks or, you know,
facebook, they're usingartificial intelligence to help
drive better results forbusiness, and so it's something
(12:43):
we should keep an eye on.
And I'll say this because, youknow, I know I've kind of gone
through a lot of this prettyquick, but before we get into a
couple other things here, I'm abig fan of history.
I am, I love history.
I love reading books from theearly part of American history,
(13:05):
whether it's thepre-revolutionary war or the
settling of the Old West.
I've always been a fan of that.
And there's an author that I, I, everybody knows who he is
louis lamore um.
Have you ever seen john wayne'shondo?
That's a louis lamore storyhe's written.
I mean, I've read every one ofhis books, uh, but one of my.
(13:27):
You know, some of my favoritebooks are books like um, the
lonesome gods or the comstockLoad or Last of the Breed is one
of my favorites, every singleone of his books.
The land is part of thechallenge.
It's almost like it's acharacter in the book because it
(13:49):
determined a lot about thestory.
Determined a lot about thestory.
I mean, for example, if youwere coming over in the you know
the early 19th century, like1820s, 1830s, and you were
planning to go out west, youknow, man, it's a six to nine
month journey.
(14:10):
When you got to Missouri, youbetter have a good wagon, you
better have a team, you betterhave a cow for milk, you better
have enough beans and bacon tolast months.
When you got going over theplains, if you went the northern
route, if you went over theplains, you had to leave at a
certain time of year because youwere going to run into winter
weather.
Going across the Rockies, theRockies, you had to go across
(14:40):
the desert.
I mean, and this was such achallenge, and we are in this
era of AI, we are in this, Ithink this paradigm change that
there is so much data and somuch information out there that
we have to plan to conquer it.
We have to conquer thisinformation to be better at what
we do, and that takes planningand it takes understanding.
(15:03):
I mean guys would learn for ayear, would study for a year and
plan for a year before theymade the crossing to get out to
California.
I mean it was a big deal and Ithink if you're farming now you
need to be planning what you cando to mitigate risk, because if
you farm you know it's a gambleevery year and understanding
(15:25):
how we can use these tools tomitigate our risk, to make the
passage safer.
I mean the planning, theunderstanding, and I see these
parallels in you know,technological changes.
I mean imagine going from youknow where you had to cross the
plains with a horse and a wagonto where you can drive in your
(15:48):
air conditioner, yourtemperature controlled car at 80
miles an hour and cross fromcoast to coast in just a matter
of days To where now you can.
Instead of sending letters topeople you haven't seen in years
, you can now pick up the phoneand talk to them almost
instantly, anywhere they are Tonow understanding massive
(16:12):
amounts of data Imagine weatheris one of the most complex data
sets that there is and we havetools now that allow us to
analyze that for our specificlocation.
And as we understand thosethings, what does that do for us
?
It allows us to make betterdecisions.
(16:33):
It allows us to make betterdecisions.
It allows us to make moreinformed choices.
Farming is still up to us and Imean if we went in there and
asked here, we'll do it rightnow, just to We'll ask this
question.
Hey, hay bot, I've got aquestion for you.
Speaker 2 (16:53):
Sure thing, John.
What's your question?
Speaker 1 (16:55):
In the middle of winter.
Would you get outside thetractor for me and take net wrap
off of my hay?
I hate that job.
Speaker 2 (17:02):
I can imagine that's a tough job, especially in the
cold, but I'm here to keep youcompany and offer any tips if
you need them.
I'm here to keep you companyand offer any tips if you need
them.
Speaker 1 (17:12):
I think those kind of things that we have to do as
farmers are they're always goingto be the things we have to do
but when we can make betterdecisions on livestock, when we
can have somebody monitor ourstock 24 hours a day and know
when we have to be out there tocheck calving, for example, I
mean, imagine being, you know, acow-calf operator.
(17:34):
You got 250, 350 mamas andyou're going into calving season
and you sleep perfectly sound.
You're asleep at night until asensor tells you that that
mama's going into labor.
Well, you better get up and getout there, because you know it
doesn't take long for a cow.
If that cow prolapses, oranything like that, you want to
(17:55):
be out there, but you don't wantto waste an entire night if you
don't have to, because there'sother things that you have to do
.
So I think there are times whenwe have to.
You know, look at the future asnot this big, scary thing, but
as how can it help us do thejobs we currently do better Now?
(18:17):
Are there risks with AI?
Are there things that we shouldbe afraid of?
Yes, and I think it's importantfor us to stay abreast of
policies regarding AI, imaginethis that you are using company
(18:41):
A we won't name any companies,but imagine you're using a
company's services to monitoryour crops and it sees a soil
deficiency because you havesensors.
So this program, this AI, knowsthat you have a soil deficiency
and it needs to recommendfertilizer.
Well, because of who owns thatAI and who's in control, and
(19:08):
because it has your data who'sin control and you know, because
of it has your data it can nowrecommend fertilizer.
That may or may not be the bestapplication, but it's owned by
the company, so that AI isgiving you what you think may be
the best information, but ithas.
It is programmed to haveloyalty to the company, to
(19:29):
recommend a company product or aprescription from that company,
and I think that's really,really important for us to
understand those relationshipsand I hope that's where
regulation you know withcompanies, because we don't know
.
There's no way to stay on topof that.
There has to be some way, andif you listen to this podcast,
(19:49):
you know I hate governmentregulations.
I hate them.
I think there are a few thingsthat the government needs to do,
because it can do it betterthan anybody else, but there's
only a few of them.
That's it, just a few of them.
But I think in AI there needsto be some sort of oversight,
(20:10):
whether it's governmental,whether it's private, that tells
us what loyalties that AI isgenerating that information for.
Again, I mean, their fertilizermight be $400 a ton, whereas
you can go down the road and buythe same, a similar fertilizer
that may be better for your soil, for $50 a ton.
(20:31):
Those are the sort of thingsthat we have to worry about.
I think the other big thing isdata ownership.
I really believe that you me,everybody, we should own our own
data.
We should own our own data andif we don't, we should make sure
(20:52):
that we, that it does not thatthat data ownership if it goes
away, if that data goes away, itdoes not impact our business.
So you know, I think there'ssome some issues with data
ownership, with becomingdependent on big tech or big ag.
I know we use John DeereOperations Center.
(21:13):
I mean it's an okay program.
I think they've.
You know it's going through agrowing phase again.
Is it perfect?
No, if you do everything inthere now, you're tied to John
Deere.
Now do you own your data?
I don't know.
We got to go read the fineprint on that.
There's nothing I do in JohnDeere that I couldn't recreate
(21:33):
in a couple hours somewhere else.
I think those are really thethree main issues that I worry
about Data ownership dependence,becoming dependent on one
technology or one company, andthen the bias and misinformation
.
You know that's a big one forme If you listen to several
podcasts.
(21:54):
I've talked about media biasand information bias, and I
think AI if it's not, if we'reusing a data set from a company
that we may not know the fullownership of this AI could be
biased towards that as company'sproducts and recommend those
things to us even though theymay not be, you know, the best
(22:15):
solution you know.
So, kind of to wrap up, I'djust like to say I don't think
we need to be afraid of AI.
I really don't.
I mean, we've all seen theTerminator.
I don't think that AI is goingto rise up and try to take over
humanity, and that's not what Iworry about.
What I worry about is greedCompanies using, you know, using
(22:39):
the AI tech to makerecommendations to us without
giving, without us having accessto all of our information.
Again, soil fertilizerrecommendations you know medical
.
Imagine that in medical.
Again, soil fertilizerrecommendations.
You know medical.
Imagine that in medical.
You know AI in medicine isgoing to be huge.
I mean there are going to be inthe next 10 years.
There are going to be hugerevolutions in medicine.
(23:02):
I would not be surprised in 20years to see a cure to cancer.
And you know you may think I'mjoking, I'm not.
I think that what would take ahuman being years, a doctor, a
PhD in data science years tostudy could be done by an AI
(23:26):
minutes or hours.
I think these are the thingswhere it really has the ability
to be a great help to humanity.
What I'm concerned about is thenature of man and woman.
I don't want to bediscriminatory, man and woman
but the nature of man to biasthe outcome to their benefit.
(23:50):
To bias the outcome to theirbenefit.
So when a medical AI recommendsmedication for you, are they
recommending a certain company'smedication or are they
recommending what's best for you?
Where is the loyalty of thatdata?
Is that data loyal to you anddoing what's best for you, or
loyal to the company and doingwhat's best for the company?
(24:11):
So you know, those are thingsto think about.
I think this is a time to beexcited about what's coming.
I really do and I think youknow you've heard me talk about
it before.
In chaos, there's opportunityand as small farms, I think
there are places we can be usingAI right now and using it
effectively.
It's not expensive.
(24:32):
Get in there and start learningit.
But we should be payingattention to policy, because any
policy that's coming out aboutAI regulations, especially when
it comes to health care, but inall forms of business that there
has to be some oversight,because it can get really bad
(24:54):
for us really quickly if wedon't watch it.
And with that, have a wonderfulday, good luck and God bless.
Popular Podcasts
On Purpose with Jay Shetty
I’m Jay Shetty host of On Purpose the worlds #1 Mental Health podcast and I’m so grateful you found us. I started this podcast 5 years ago to invite you into conversations and workshops that are designed to help make you happier, healthier and more healed. I believe that when you (yes you) feel seen, heard and understood you’re able to deal with relationship struggles, work challenges and life’s ups and downs with more ease and grace. I interview experts, celebrities, thought leaders and athletes so that we can grow our mindset, build better habits and uncover a side of them we’ve never seen before. New episodes every Monday and Friday. Your support means the world to me and I don’t take it for granted — click the follow button and leave a review to help us spread the love with On Purpose. I can’t wait for you to listen to your first or 500th episode!
The Breakfast Club
The World's Most Dangerous Morning Show, The Breakfast Club, With DJ Envy And Charlamagne Tha God!
The Joe Rogan Experience
The official podcast of comedian Joe Rogan.