March 10, 2025 • 9 mins
Think ChatGPT is the only AI tool you need? Think again. In this episode, we dive into why relying on just one AI tool is holding you back—and how a stacked AI system can dramatically boost your productivity.
Inventium’s resident AI expert, Neo Aplin, joins Dr. Amantha Imber to break down:
- Why AI stacking is a game-changer – The biggest mistake people make when using AI? Thinking one tool can do it all. We break down how combining different AI models can give you better, faster, and more accurate results.
- The right tool for the right job – ChatGPT is great, but what if there’s a tool that can summarise long documents twice as fast or generate images way more realistically? We explore the strengths and weaknesses of top AI tools and when to use each one.
- How to build your AI workflow – Whether you're an entrepreneur, creator, or business professional, we share a simple system for integrating multiple AI tools into your daily workflow. More efficiency, less frustration.
- AI tool recommendations – Get our curated list of must-use AI tools that complement ChatGPT and take your productivity to the next level.
If you’re serious about making AI work for you, stop thinking small—start stacking.
Want to master AI productivity? Check out Inventium’s Gen AI Productivity System—a self-paced course designed to help you boost productivity and save hours every week by using AI smarter. Learn more at https://inventium.com.au/GenAI/
My latest book The Health Habit is out now. You can order a copy here: https://www.amantha.com/the-health-habit/
Connect with me on the socials:
Linkedin (https://www.linkedin.com/in/amanthaimber)
Instagram (https://www.instagram.com/amanthai)
If you are looking for more tips to improve the way you work and live, I write a weekly newsletter where I share practical and simple to apply ti
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Speaker 1 (00:00):
At nine am on a Tuesday and you're working on
an important project and decide to use Jenai for some help.
But what if I told you that relying on just
one Jenai is like asking just one single expert for
advice when you can have an entire panel of specialists.
For the last two years, I've been using jeni daily,
(00:21):
and one of the biggest game changes has been treating
AI like a think tank rather than a single assistant.
Different AI models have unique strengths, and by strategically combining them,
you can dramatically enhance the quality of your work. And
that's what today's episode is all about. I am joined
(00:41):
by Inventium's resident AI expert, Neo Afflin to unpack how
you can leave ridge multiple Genai tools to turn them
into your personal advisory board. So whether you're writing, strategizing,
or problem solving, this approach could completely transform the way
you use Genai. Just quickly before we get into today's episode,
(01:03):
if you want to go DeFi and learn how to
work with AI instead of worrying about being replaced by it,
I have something that I think you will love, but
my consultancy you invent him. We've created the Jenai productivity system.
It's a self paced online course designed to help you
boost productivity and save literally hours every week by using
(01:25):
Jenai a whole lot smarter. In just a few hours,
you'll go from Jenai dabbler to Jenai expert with practical
tools you can start using immediately. Head to inventium dot
com dot au forward slash Jnai to check it out
and get started today. Welcome to How I Work, a
(01:48):
show about habits, rituals, and strategies for optimizing your day.
I'm your host, doctor Amantha imber So. A lot of
people out there just rely on one NAI tool like
Copilot or chat GPT. I'm curious as to why you
think that might actually limit the results that someone is
(02:08):
getting from the Genai.
Speaker 2 (02:10):
The first thing I'd say to that is the Genais
are brilliant, and you're getting great results out of a
lot of these different Genais. So take this as a
next level thing. But you'll find that each of the
Ai tools have their own abilities, and some of them
are better at certain things than others, and so using
more than one Genai tool will give you more than
(02:32):
one perspective.
Speaker 1 (02:34):
I know that something that you do a lot of
is using multiple genais as a feedback loop. Can you
tell me a bit more about what you're doing here.
Speaker 2 (02:44):
When I'm writing something, or I'm doing deep analysis, or
I'm working with a client on something, then I want
to get the best result. And so what I'm doing
is I'm working deeply with one GENAI to get one perspective,
and generally it's more about industry knowledge or structure or
problem solving or which things could be included. And then
(03:04):
I'll do exactly the same work on a completely different GENAI.
So I might use chat GPT for one of them,
and then I'll go to Claude and do the same
amount of work on Claude and get Claude's perspective. And
what I'll find is Claude will come up with things
that chat TIPT may not.
Speaker 1 (03:20):
Do you remember what inspired you to take this approach
in the first place.
Speaker 2 (03:23):
Maybe it's because I'm a bit of a GENAI geek
and I want to just try all the different genis.
But what I found is that going to each of
them gives me a different perspective, not just on knowledge.
By the way, I will say this on language. Going
to one, from one to the other, you might find
better ways to phrase a sentence or phrase a paragraph,
So it's same principles apply even with writing.
Speaker 1 (03:47):
It's great. I've heard you compare using multiple genais to
having a room full of expert consultants. Could you just
expand on what you mean by that.
Speaker 2 (03:57):
Yeah, it's almost like having two rooms. Like you've got
one room of consultants because you've got to CHATCHAPT and
then get a completely different room of consultants with Claude
or with Gemini or any of the others, because they've
got different ways that they've absorbed their knowledge and different
ways that they kind of work through that knowledge. So
you get two different sets of opinions back, which I love.
Speaker 1 (04:19):
Now. I've heard you say that different GENAI models have
different strengths and weaknesses, and I imagine that people listening
have their favorite, or they go to one or maybe
the one the only one that they're not blocked from
using at their workplace. I would love to know if
you could briefly break down with the major genais that
(04:40):
people are using, which what like, what are the things
that each one is particularly good at.
Speaker 2 (04:47):
So let's start with a big granddaddy CHATCHPT, which is
great for analysis logic general, it's an awesome everyday workhorse,
fantastic for that. It's also got very good logic tools
if you want to use the one and the three models.
So if you need analysis and maths and stuff like that,
brilliant for that. If you're a writer, go for Claude.
(05:10):
Claude just out of the box, sounds a lot more
like a human than an AI and I'm particularly impressed
what they do on safety as well. So with writing,
they're just great. Also with coding, it does coding and
development problems a lot better than others. Gemini, I've got
to say, is really impressed me. They've come up with
a Google Gemini. They've come up with a lot more,
(05:34):
more tools, better, better models. It's not perfect yet, but
don't discount googling this one. This race is going to
be hotly contested and Google's going to be up there
with everyone. So have a play with that at the
moment that it's free, so definitely jump in and have
a dive. Copilot is excellent for the workforce. I personally
(05:55):
don't find it as user friendly as chat GPT, but
the way it locks down for your workforce is And
then do have a play with the others as well.
They're also good fun.
Speaker 1 (06:04):
Okay, so can you walk me through a real world
example of using multiple genais to improve a piece of work?
And I'm thinking, let's say I do a lot of
business development work and part of my role, so creating
a sales proposal is something that I do a lot of.
(06:27):
So how would you recommend that I do that better?
Speaker 2 (06:31):
Yeah? I do it in two chunks. One is the
structure and pitch and what you're trying to put together.
I'd work with say, chat YOURPT first, and then say
how should I structure it. Here's my goals, here's my customers,
ask questions and have a discussion with it, and then
totally separate to that. Do the same thing in claude
(06:52):
and then you'll get a structure. Once you've got that,
you've then got two opinions on what you should cover,
and then you've then built yourself out of the two
structure you want and the goals and kind of points
you want to cover. Once you've got that, do the
same thing with the actual writing. So say here's a
couple of paragraphs, let's flesh that out together. Do that
with chat GPT, and then do it with Claude and
you'll see you'll get two different results.
Speaker 1 (07:13):
What are some other key factors that we might need
to consider when structuring a MULTIAI feedback loop.
Speaker 2 (07:20):
Well, first off, don't overcope complicate it. Not every problem
needs to go to two different ais. But I would
use it less about the writing. It's more about the ideas.
So if you've got a complex thing you're not quite
sure about the ideas or the structure of a document
or some kind of analysis paper or a pitch deck
or something like that, these are the great things to
(07:41):
go do for two opinions. They're analysis or thinking deeply
through things, structure of documents, kind of what's right or wrong,
pros and cons. Those kind of things are brilliant to
do the two model approach. If you're doing just say writing,
it's probably not as appropriate or not as needed to
go to the two ais. But yeah, ideas constructs, those
(08:03):
kind of things brilliant.
Speaker 1 (08:04):
Is there a point of diminishing returns, like when you
should just stop it with all the genais and just
go okay, we're done here.
Speaker 2 (08:13):
Absolutely, And I'm guilty of trying them out because I
enjoy trying them out, But I think for most people, yeah,
I think just only a few times that you would
need to particularly on those deep problem solving things, and
don't need to do it all the time. But if
you've got those problems solving things, it's a really powerful tool.
Speaker 1 (08:32):
Okay. So for someone listening today who wants to get
in and start trying this immediately, what is the easiest
way to get started?
Speaker 2 (08:39):
First off, sign up to the different tools, sign up
to Claude, chat, EPG, Gemini, try it the others if
you'd like, and then just play with them and see
the different opinions. You get back on some of the
problems you're solving, and then you might find that certain
tools are better for certain problems.
Speaker 1 (08:57):
Thank you so much, Neo. I'm feeling very inspire to
use this strategy today. Thank you so much. If you're
keen to learn even more Genai tricks and hacks, check
out Inventium's Jenai Productivity System. It's a self faced course
to transform you from a Jenai dabbler to jenaipro in
(09:19):
just a few hours. Head to inventium dot com dot
au forward slash Jenai to check it out and get
started today. If you like today's show, make sure you
hit follow on your podcast app to be alerted when
new episodes drop. How I Work was recorded on the
traditional land of the Warringery people, part of the Cooler Nation.
(09:40):
A big thank you to Martin Nimber for doing the
sound mix.
At nine am on a Tuesday and you're working on
an important project and decide to use Jenai for some help.
But what if I told you that relying on just
one Jenai is like asking just one single expert for
advice when you can have an entire panel of specialists.
For the last two years, I've been using jeni daily,
(00:21):
and one of the biggest game changes has been treating
AI like a think tank rather than a single assistant.
Different AI models have unique strengths, and by strategically combining them,
you can dramatically enhance the quality of your work. And
that's what today's episode is all about. I am joined
(00:41):
by Inventium's resident AI expert, Neo Afflin to unpack how
you can leave ridge multiple Genai tools to turn them
into your personal advisory board. So whether you're writing, strategizing,
or problem solving, this approach could completely transform the way
you use Genai. Just quickly before we get into today's episode,
(01:03):
if you want to go DeFi and learn how to
work with AI instead of worrying about being replaced by it,
I have something that I think you will love, but
my consultancy you invent him. We've created the Jenai productivity system.
It's a self paced online course designed to help you
boost productivity and save literally hours every week by using
(01:25):
Jenai a whole lot smarter. In just a few hours,
you'll go from Jenai dabbler to Jenai expert with practical
tools you can start using immediately. Head to inventium dot
com dot au forward slash Jnai to check it out
and get started today. Welcome to How I Work, a
(01:48):
show about habits, rituals, and strategies for optimizing your day.
I'm your host, doctor Amantha imber So. A lot of
people out there just rely on one NAI tool like
Copilot or chat GPT. I'm curious as to why you
think that might actually limit the results that someone is
(02:08):
getting from the Genai.
Speaker 2 (02:10):
The first thing I'd say to that is the Genais
are brilliant, and you're getting great results out of a
lot of these different Genais. So take this as a
next level thing. But you'll find that each of the
Ai tools have their own abilities, and some of them
are better at certain things than others, and so using
more than one Genai tool will give you more than
(02:32):
one perspective.
Speaker 1 (02:34):
I know that something that you do a lot of
is using multiple genais as a feedback loop. Can you
tell me a bit more about what you're doing here.
Speaker 2 (02:44):
When I'm writing something, or I'm doing deep analysis, or
I'm working with a client on something, then I want
to get the best result. And so what I'm doing
is I'm working deeply with one GENAI to get one perspective,
and generally it's more about industry knowledge or structure or
problem solving or which things could be included. And then
(03:04):
I'll do exactly the same work on a completely different GENAI.
So I might use chat GPT for one of them,
and then I'll go to Claude and do the same
amount of work on Claude and get Claude's perspective. And
what I'll find is Claude will come up with things
that chat TIPT may not.
Speaker 1 (03:20):
Do you remember what inspired you to take this approach
in the first place.
Speaker 2 (03:23):
Maybe it's because I'm a bit of a GENAI geek
and I want to just try all the different genis.
But what I found is that going to each of
them gives me a different perspective, not just on knowledge.
By the way, I will say this on language. Going
to one, from one to the other, you might find
better ways to phrase a sentence or phrase a paragraph,
So it's same principles apply even with writing.
Speaker 1 (03:47):
It's great. I've heard you compare using multiple genais to
having a room full of expert consultants. Could you just
expand on what you mean by that.
Speaker 2 (03:57):
Yeah, it's almost like having two rooms. Like you've got
one room of consultants because you've got to CHATCHAPT and
then get a completely different room of consultants with Claude
or with Gemini or any of the others, because they've
got different ways that they've absorbed their knowledge and different
ways that they kind of work through that knowledge. So
you get two different sets of opinions back, which I love.
Speaker 1 (04:19):
Now. I've heard you say that different GENAI models have
different strengths and weaknesses, and I imagine that people listening
have their favorite, or they go to one or maybe
the one the only one that they're not blocked from
using at their workplace. I would love to know if
you could briefly break down with the major genais that
(04:40):
people are using, which what like, what are the things
that each one is particularly good at.
Speaker 2 (04:47):
So let's start with a big granddaddy CHATCHPT, which is
great for analysis logic general, it's an awesome everyday workhorse,
fantastic for that. It's also got very good logic tools
if you want to use the one and the three models.
So if you need analysis and maths and stuff like that,
brilliant for that. If you're a writer, go for Claude.
(05:10):
Claude just out of the box, sounds a lot more
like a human than an AI and I'm particularly impressed
what they do on safety as well. So with writing,
they're just great. Also with coding, it does coding and
development problems a lot better than others. Gemini, I've got
to say, is really impressed me. They've come up with
a Google Gemini. They've come up with a lot more,
(05:34):
more tools, better, better models. It's not perfect yet, but
don't discount googling this one. This race is going to
be hotly contested and Google's going to be up there
with everyone. So have a play with that at the
moment that it's free, so definitely jump in and have
a dive. Copilot is excellent for the workforce. I personally
(05:55):
don't find it as user friendly as chat GPT, but
the way it locks down for your workforce is And
then do have a play with the others as well.
They're also good fun.
Speaker 1 (06:04):
Okay, so can you walk me through a real world
example of using multiple genais to improve a piece of work?
And I'm thinking, let's say I do a lot of
business development work and part of my role, so creating
a sales proposal is something that I do a lot of.
(06:27):
So how would you recommend that I do that better?
Speaker 2 (06:31):
Yeah? I do it in two chunks. One is the
structure and pitch and what you're trying to put together.
I'd work with say, chat YOURPT first, and then say
how should I structure it. Here's my goals, here's my customers,
ask questions and have a discussion with it, and then
totally separate to that. Do the same thing in claude
(06:52):
and then you'll get a structure. Once you've got that,
you've then got two opinions on what you should cover,
and then you've then built yourself out of the two
structure you want and the goals and kind of points
you want to cover. Once you've got that, do the
same thing with the actual writing. So say here's a
couple of paragraphs, let's flesh that out together. Do that
with chat GPT, and then do it with Claude and
you'll see you'll get two different results.
Speaker 1 (07:13):
What are some other key factors that we might need
to consider when structuring a MULTIAI feedback loop.
Speaker 2 (07:20):
Well, first off, don't overcope complicate it. Not every problem
needs to go to two different ais. But I would
use it less about the writing. It's more about the ideas.
So if you've got a complex thing you're not quite
sure about the ideas or the structure of a document
or some kind of analysis paper or a pitch deck
or something like that, these are the great things to
(07:41):
go do for two opinions. They're analysis or thinking deeply
through things, structure of documents, kind of what's right or wrong,
pros and cons. Those kind of things are brilliant to
do the two model approach. If you're doing just say writing,
it's probably not as appropriate or not as needed to
go to the two ais. But yeah, ideas constructs, those
(08:03):
kind of things brilliant.
Speaker 1 (08:04):
Is there a point of diminishing returns, like when you
should just stop it with all the genais and just
go okay, we're done here.
Speaker 2 (08:13):
Absolutely, And I'm guilty of trying them out because I
enjoy trying them out, But I think for most people, yeah,
I think just only a few times that you would
need to particularly on those deep problem solving things, and
don't need to do it all the time. But if
you've got those problems solving things, it's a really powerful tool.
Speaker 1 (08:32):
Okay. So for someone listening today who wants to get
in and start trying this immediately, what is the easiest
way to get started?
Speaker 2 (08:39):
First off, sign up to the different tools, sign up
to Claude, chat, EPG, Gemini, try it the others if
you'd like, and then just play with them and see
the different opinions. You get back on some of the
problems you're solving, and then you might find that certain
tools are better for certain problems.
Speaker 1 (08:57):
Thank you so much, Neo. I'm feeling very inspire to
use this strategy today. Thank you so much. If you're
keen to learn even more Genai tricks and hacks, check
out Inventium's Jenai Productivity System. It's a self faced course
to transform you from a Jenai dabbler to jenaipro in
(09:19):
just a few hours. Head to inventium dot com dot
au forward slash Jenai to check it out and get
started today. If you like today's show, make sure you
hit follow on your podcast app to be alerted when
new episodes drop. How I Work was recorded on the
traditional land of the Warringery people, part of the Cooler Nation.
(09:40):
A big thank you to Martin Nimber for doing the
sound mix.
Popular Podcasts
Las Culturistas with Matt Rogers and Bowen Yang
Ding dong! Join your culture consultants, Matt Rogers and Bowen Yang, on an unforgettable journey into the beating heart of CULTURE. Alongside sizzling special guests, they GET INTO the hottest pop-culture moments of the day and the formative cultural experiences that turned them into Culturistas. Produced by the Big Money Players Network and iHeartRadio.
40s and Free Agents: NFL Draft Season
Daniel Jeremiah of Move the Sticks and Gregg Rosenthal of NFL Daily join forces to break down every team's needs this offseason.
Crime Junkie
Does hearing about a true crime case always leave you scouring the internet for the truth behind the story? Dive into your next mystery with Crime Junkie. Every Monday, join your host Ashley Flowers as she unravels all the details of infamous and underreported true crime cases with her best friend Brit Prawat. From cold cases to missing persons and heroes in our community who seek justice, Crime Junkie is your destination for theories and stories you won’t hear anywhere else. Whether you're a seasoned true crime enthusiast or new to the genre, you'll find yourself on the edge of your seat awaiting a new episode every Monday. If you can never get enough true crime... Congratulations, you’ve found your people. Follow to join a community of Crime Junkies! Crime Junkie is presented by audiochuck Media Company.