1

2
Table of Contents

Preface ...................................................................................................... 6
Visionaries Predict the Future of AI .................................................... 9
Visionary Nick Bostrom ........................................................................................... 9
Visionary Ethan Mollick ......................................................................................... 11
Visionary Kai-Fu Lee.............................................................................................. 14
Visionary Nigel Toon .............................................................................................. 15
Visionary Ray Kurzweil .......................................................................................... 18

Next-Gen Chatbots from Tech Giants .............................................. 20

OpenAI ChatGPT-4o............................................................................................... 21
Google Gemini & Project Astra ............................................................................. 31
Microsoft CoPilot .................................................................................................... 35
Apple Intelligence ................................................................................................... 37

Will AI Take Over Your Job? ................................................................ 43

New Work, New World .......................................................................................... 44
Preparing for Tomorrow’s Workforce................................................................47
AI-Driven Societal Transformations .................................................................. 51
Everybody Loves Andrew ......................................................................................54
Who Will AI Replace Next? .................................................................................... 55

The Massive Reach of ChatGPT .......................................................... 58

ChatGPT: Going Mainstream............................................................................... 62

Unlocking Retrieval-Augmented Generation ................................ 64

To RAG or Not to RAG? .......................................................................................... 65
RAG vs. Transfer Learning: What’s the Difference? ....................................... 66
RAG vs. LLM: A Comparative Look ..................................................................... 67
Is RAG the Holy Grail of Enterprise AI? ..............................................................70
Amazon’s AI Secret Weapon ................................................................................. 72

Who’s Leading the AI Patent Race? ................................................... 74

3
AI Revolutionizing the Travel Industry ............................................ 78
How Travelers Are Embracing AI ....................................................................... 80
Actionable Travel Recommendations with AI .................................................. 81
Travel Experts Weigh In on ChatGPT ................................................................ 84
The Ultimate Trip Planner with AI ......................................................................87

The Rise of AI Computers .................................................................... 92

Inside Microsoft Hardware Innovations ........................................................... 92
Microsoft Software: The AI Edge .........................................................................93
The Microsoft Prompting Playbook ................................................................... 94
Exploring Small Language Models (SLM) ........................................................ 96

AI Agents: The Future Workforce ...................................................... 97

Key Components of Powerful AI Agents ........................................................... 97
Different Types of AI Agents Explained ............................................................ 97
Real-World AI Agent Applications ..................................................................... 98
Why AI Agents Are Game-Changers .................................................................. 99
Advanced AI Agents in Action ............................................................................. 99

Global AI Adoption: A Revolution in Progress .............................. 103

The Ultimate AI Preparedness Index ................................................................ 103
Inside the AI Preparedness Index ...................................................................... 104
Why AI Preparedness Matters ............................................................................ 105
Top Countries Leading in AI Adoption ............................................................. 105
The Rise of Generation AI.................................................................................... 108

Postface ................................................................................................. 110

The Generative AI CA$H Machine Book Series .............................. 112
➜ Glossary ............................................................................................ 116
➜ Indispensable AI Tools ................................................................... 119
➜ Learn How to Generate a Passive $30K/month ........................ 127

4
AI Unleashed: Revolutionizing Our World with Cutting-Edge Technology

Volume 5 – Generative AI CA$H MACHINE Series

Copyright © 2024 by Borneo AG

Book Cover by Borneo Creatives

All rights reserved. You cannot copy, share, or use anything from this book
without written permission from the author or publisher.

Legal Notice:

This book is for your personal use only. Do not change, share, sell, use, quote,
or reword anything in this book without permission.

Disclaimer:

This book is for learning and fun. We have tried to make sure everything is
accurate and complete, but we do not guarantee anything. The author is not
giving legal, financial, medical, or professional advice. Always check with a
licensed professional before trying anything from this book. By reading this,
you agree that the author is not responsible for any losses or problems that
arise from using this information, including any mistakes, or missing details.

First Edition July 2024

CK-163639-001

5
Preface
Welcome to "AI Unleashed: Revolutionizing Our World with Cutting-Edge
Technology," a journey into the transformative world of artificial
intelligence (AI). This book is for anyone interested in understanding how AI
is reshaping our daily lives, industries, and the future. Whether you're a tech
enthusiast, a business professional, or simply curious about AI, this book will
provide you with valuable insights and practical knowledge.

In this volume, we delve into the minds of visionaries who are at the forefront
of AI development. You'll learn from experts like Nick Bostrom, Ethan
Mollick, Kai-Fu Lee, Nigel Toon, and Ray Kurzweil, who share their thoughts
on how AI will revolutionize various sectors. From healthcare to
transportation, and from education to creative arts, AI is making its presence
felt in every corner of our lives.

Our goal is to present complex ideas in simple, actionable terms. You'll

discover how AI can enhance personal convenience, improve healthcare
outcomes, transform employment landscapes, and even tackle global
challenges like climate change. We'll explore the ethical and governance
issues that come with these advancements, ensuring you understand both the
opportunities and the responsibilities of this powerful technology.

Moreover, we highlight practical applications of AI, showing you how to

leverage it in your daily life and work. From using AI as a collaborative partner
to understanding the implications of general AI and superintelligence, this
book provides a comprehensive overview that is both informative and
inspiring.

As you read the chapters, you'll find that AI is not just a distant futuristic
concept but a tangible force that is already shaping our present and will
continue to define our future. Get ready to embark on a journey that will

6
expand your horizons and equip you with the knowledge to navigate the AI-
driven world with confidence.

7
AI
Unleashed

Volume 5
8
Visionaries Predict the Future of AI

We will start off here with some lessons from a few of my favorite visionaries:

• Nick Bostrom (Superintelligence: Paths, Dangers, Strategies; Deep Utopia:

Life and Meaning in a Solved World)

• Ethan Mollick (Co-Intelligence: Living and Working with AI)

• Kai-Fu Lee (AI 2041: Ten Visions for our Future; AI Superpowers: China,
Silicon Valley, and the New World Order)

• Nigel Toon (How AI Thinks: How we built it, how it can help us, and how
we can control it)

• Ray Kurzweil (The Singularity is Nearer: when we merge with AI)

Visionary Nick Bostrom

Bostrom explores the implications of solving major
humanitarian and societal problems through advanced
technology, including AI. He raises critical questions
about the meaning and purpose of human life in a world
where traditional challenges are absent, emphasizing
the need for careful consideration of the values and
objectives that should guide us in a potentially "solved"
world, where existential and ethical dilemmas persist.

The future of artificial intelligence (AI) is both expansive and transformative,

impacting various aspects of society, economy, and daily life. According to
Bostrom:

• Integration into Daily Life: AI is becoming even more integrated

into everyday activities with more sophisticated personal

9
 assistants, advanced home automation systems, and smarter, more
context-aware applications enhancing daily convenience and
efficiency.

• Advancements in Healthcare: AI could revolutionize healthcare

through enhanced diagnostic systems, personalized medicine,
robotic surgeries, and monitoring patient health through AI-
powered devices. This could lead to better treatment outcomes and
more efficient healthcare services.

• Impact on Employment and the Economy: As AI systems become

capable of performing tasks traditionally done by humans, there
could be significant shifts in employment. Some jobs may be
automated, and new jobs created, particularly in AI development,
oversight, and maintenance. This may require large-scale
retraining and shifts in the workforce.

• Autonomous Vehicles and Transportation: Continued development

of AI could lead to the widespread adoption of autonomous vehicles,
potentially reducing accidents caused by human error, optimizing
traffic flow, and transforming transportation planning.

• Ethical and Governance Issues: As AI systems play a more crucial

role in decisions affecting human lives, ethical and governance
issues will gain prominence. Questions around privacy,
surveillance, decision-making in AI systems, and the ethical use of
AI will require robust legal and regulatory frameworks.

• AI in Creativity and Entertainment: AI will increasingly create art,

music, literature, and entertainment, challenging traditional
notions of creativity, and potentially leading to new forms of artistic
expression.

10
 • AI and Global Challenges: AI could be instrumental in addressing
global challenges like climate change and resource management. It
could improve the efficiency of systems, help in modeling climate
scenarios, and optimize the use of natural resources.

• General AI and Superintelligence: While still speculative and

controversial, the development of general AI that surpasses human
intelligence could have profound implications. This raises scenarios
that range from solving all of humanity’s problems to existential
risks if not responsibly managed.

Each of these points reflects ongoing research, debates, and the varying
trajectories AI development might take. The overall impact of AI will depend
on the directions chosen by researchers, the regulatory landscape, and the
global socio-economic conditions.

Visionary Ethan Mollick

Mollick describes co-intelligence as a partnership where AI
assists in tasks that leverage its computational strengths
while humans contribute judgment, creativity, and ethical
considerations. Here are some key aspects of using AI as
co-intelligence:

• Collaboration, Not Replacement: AI serves as a partner to human

intelligence, helping manage tasks that are computational or data-
intensive, while humans focus on aspects that require human
judgment, creativity, or ethical considerations.

11
 • Centaur and Cyborg Models: These models represent different
methods of collaboration. Centaurs maintain clear distinctions
between human and AI responsibilities, while Cyborgs integrate AI
more deeply into human tasks, creating a more fluid interaction
between human and machine capabilities.

• Enhancing Human Capabilities: By working with AI, humans can

extend their cognitive reach, allowing for improved problem-solving
and innovation. This partnership can lead to new insights and solutions
that neither humans nor AI could achieve independently.

• Adaptation and Learning: Humans must adapt and learn how to best
utilize AI, understanding both its capabilities and limitations, to
maximize the benefits of this technology. This involves staying actively
involved in the AI's operation and output to ensure it aligns with
human values and objectives.

• Ethical and Practical Considerations: It's important to maintain

human oversight to prevent misuse of AI and ensure its applications do
not compromise ethical standards. This includes monitoring AI's
actions and correcting or guiding its outputs, as necessary.

Mollick suggests treating AI as a collaborative partner or coworker in several

main ways:

• Engage with AI actively: Mollick urges us to "engage with AI as co-

worker, co-teacher and coach". This implies treating AI as an active
collaborator rather than just a passive tool.

• Use AI for everything: Mollick advises to "use it for everything you do

for an entire day". This approach helps discover how AI can aid your
workflow and potentially innovate in unexpected ways.

12
 • Leverage AI's strengths: Mollick notes that "AI is best at creative,
intellectually engaging tasks". He suggests using AI to manage tasks it
excels at, allowing humans to focus on areas where they add unique
value.

• Use AI to overcome creative blocks: Mollick recommends using AI to

"get unstuck" when facing creative challenges, such as generating
initial drafts or providing multiple options for rewriting.

• Treat AI as a person: Mollick argues that we should "treat AI as a

person because it is the most familiar subject on the actual strengths
and weaknesses we know about". This approach helps in
understanding and leveraging AI's capabilities more effectively.

• Maintain human oversight: While collaborating with AI, Mollick

emphasizes the importance of maintaining human oversight to ensure
accuracy and ethical use.

• Adapt and evolve: Recognizing that AI technology is rapidly advancing,

Mollick encourages staying adaptable and ready for future
advancements.

Using AI as co-intelligence is fundamentally about enhancing and

augmenting human abilities, not replacing them, ensuring that AI
development and application remain aligned with enhancing human welfare
and capabilities.

13
Visionary Kai-Fu Lee
AI will profoundly transform every aspect of our lives over
the next 20 years, from healthcare and education to work and
entertainment. While AI presents challenges like job
displacement and privacy concerns, Lee believes its overall
impact will be more positive than negative. Lee emphasizes
the need to prepare for this AI-driven future by retraining
workforces, adapting education systems, and addressing
ethical issues. Lee envisions AI's potential to enhance human capabilities,
drive economic growth, and potentially solve major global problems like
poverty and hunger.

Key industries impacted by AI by 2041:

• Healthcare: AI will revolutionize medicine through precision

treatments, digitized patient data, and optimized processes. AI-
powered diagnostics and personalized medicine tailored to individual
genetic profiles will become commonplace.

• Education: AI will transform learning experiences with virtual AI

teachers providing personalized guidance and support to students.
Education will become more adaptive and tailored to individual needs.

• Transportation: Autonomous vehicles will reshape mobility, making

travel safer and more efficient. This will integrate with smart city
infrastructures.

• Manufacturing: AI-driven robots and automation will streamline

production processes, reduce costs, and enhance efficiency across
industries

• Agriculture: Robotics will assist in seeding and harvesting, decreasing

costs, and increasing food production.

14
 • Entertainment: AI will blur lines between real and virtual experiences
through advanced virtual and augmented reality technologies.

• Workforce: AI and automation will replace many blue-collar and

white-collar jobs, necessitating workforce retraining and adaptation

• Financial services: AI will transform operations in the finance

industry, from trading to risk assessment.

• Retail and e-commerce: AI will revolutionize shopping experiences

and planning, with advancements in areas like autonomous delivery.

• Home automation: Household robots and AI assistants will become

more prevalent, managing various domestic tasks.

Changes will bring both opportunities and challenges, reshaping various

aspects of daily life and work by 2041.

Visionary Nigel Toon

According to Toon, AI is revolutionizing various sectors
by learning to think in ways considered uniquely human.
His book explains how AI teaches itself, enabling it to
create new images, converse in any language, and solve
complex problems. Understanding how AI thinks is
crucial as we enter a new era where machine intelligence
will significantly impact society. This knowledge will be
essential for navigating the opportunities and
challenges that arise from living in a world shared with AI.

His views about the future of AI follows:

15
 • Powerful but Controllable: Toon sees AI as a powerful tool that is
manageable and harnessed for human benefit. He believes that AI will
augment human intelligence rather than replace it entirely.

• Transformative Impact: Toon anticipates that AI will have a significant

and transformative impact across various sectors of society. He
emphasizes that AI will create enormous opportunities for those who
understand its capabilities.

• Need for Understanding: Toon stresses the importance of

understanding how AI thinks. He believes this knowledge is crucial for
effectively navigating the future and leveraging AI's potential.

• Addressing Concerns: While acknowledging the power of AI, Toon also

recognizes the need to address concerns surrounding its development
and implementation. This includes potential risks and ethical
considerations.

• Augmentation, Not Replacement: Toon's perspective seems to lean

towards AI as a tool for augmenting human capabilities rather than
completely replacing human roles - humans and AI working
collaboratively.

• Societal Preparation: Toon advocates for broader education and

awareness about AI among business leaders, educators, students, and
the public. He believes this preparation is essential for society to adapt
to and benefit from AI advancements.

Toon describes the future of AI across various industries with optimism and
caution. AI will significantly impact multiple sectors:

• Healthcare: AI will enhance diagnostic accuracy, streamline

workflows, and provide personalized treatments, leading to improved
patient outcomes and efficiency in hospitals.

16
• Education: AI will support personalized learning, allowing teachers to
focus more on developing critical thinking and creativity in students,
rather than on repetitive tasks.

• Manufacturing: AI will optimize manufacturing processes, reduce

carbon emissions, and improve efficiency, particularly in energy-
intensive industries like cement and steel production.

• Energy: AI will play a crucial role in advancing clean energy

technologies, such as nuclear fusion, and optimizing power
consumption in data centers.

• Finance: AI will enhance predictive analytics, fraud detection, and

personalized financial services, contributing to more secure and
efficient financial systems.

• Transportation: Autonomous transport systems will become more

prevalent, improving safety and efficiency in planning and personal
travel.

• Creative Arts: AI will have a transformative effect on the creative arts.

This includes AI-generated art, music, and other forms of creative
content.
• Software Development: AI will be capable of writing code instantly,
suggesting a significant impact on the software development industry.
• Scientific Research: Toon calls it AI's ability to unfold "the elaborate
3D puzzles of proteins," indicating its potential in accelerating
scientific discoveries, particularly in fields like biochemistry and
molecular biology.

17
Visionary Ray Kurzweil
According to Kurzweil, the integration of AI with human
capabilities will lead to transformative advancements. This
merger will result in superhuman intelligence,
revolutionizing fields such as medicine, technology, and
daily life. Kurzweil also emphasizes the exponential growth
of AI capabilities and the profound societal changes that will
follow, highlighting both the opportunities and challenges
of this technological evolution.

Kurzweil has some bold predictions for the future of generative AI as

characterized by optimism and a belief in rapid, transformative progress.

• Accelerated Progress - Kurzweil notes that generative AI has

advanced faster than many expected, with models like GPT-3 and
GPT-4 achieving significant milestones in understanding and
generating human-like text and images.

• AGI Achievement by 2029 - He maintains his long-standing

prediction that artificial general intelligence (AGI) is achievable by
2029. This AGI would match human-level intelligence across a wide
range of cognitive tasks.

• Creative and Human-like Capabilities - Kurzweil emphasizes that

generative AI models are exhibiting genuine creativity and
performing tasks previously thought to be uniquely human. He sees
this as a crucial step towards more advanced AI systems.

• Integration with Human Intelligence -Rather than viewing AI as a

competitor, Kurzweil envisions a future where AI and human
intelligence merge. He predicts that this integration will lead to
unprecedented advancements in various fields.

18
 • Singularity by 2045 - Kurzweil forecasts the arrival of Singularity
by 2045, when humans will fuse with AI, dramatically enhancing
our intelligence and capabilities. He believes this will result in a
profound transformation of human civilization.

• Exponential Growth - He emphasizes the importance of

understanding the exponential growth in AI capabilities, driven by
increasing computational power and algorithmic improvements.

• Challenges and Limitations - While optimistic, Kurzweil

acknowledges current limitations in generative AI, such as
"hallucinations" where models generate plausible but incorrect
information - he remains confident technology can overcome these
challenges.

Kurzweil's predictions paint a picture of generative AI as a transformative

technology that will not only match but eventually surpass human
intelligence, leading to a future where the boundaries between human and
artificial intelligence blur. His vision is one of symbiosis rather than
competition between humans and AI.

19
Next-Gen Chatbots from Tech Giants

As expected, Microsoft and Google are leaning towards making their

generative AI technologies work within their suite of office tools. Meanwhile,
OpenAI is trailblazing again with powerful features and licensing their LLMs
to corporations. Apple is integrating ‘Apple Intelligence’ (AI) into MacOS and
iOS seamlessly.

Recent report from Microsoft shows that 2024 is the year AI at work becomes
real.

• Employees want AI at work—and they won’t wait for companies to

catch up. They’re bringing their own tools even as leaders face AI
inertia. For employees, AI raises the bar and breaks the career ceiling.
Some are itching for a career change, and there is a massive
opportunity for those willing to skill up on AI.

• The rise of the AI power user—and what they reveal about the future.
Power users use AI at least several times per week. They say it saves
them more than 30 minutes per day.

In the age of AI, forward-looking leaders are already prioritizing

communication skills when they hire. The future of tech is going to be more
like having a conversation and less like using a calculator.

Sometimes we learn things just in what we say to AI, and then sometimes we
learn things from what the machine responds with. And then there are times
when you don’t even understand what question you want to ask AI, and it
ends up helping you understand what you’re trying to get at.

Leaders should absolutely use AI as a sounding board or a stand-in to game

out different scenarios or rehearse difficult conversations.

20
OpenAI ChatGPT-4o
First came HAL. Then came Her. Now comes ChatGPT-4o.

ChatGPT-4o (“o” for “omni”) is a step towards much more natural human-
computer interaction—it accepts as input any combination of text, audio,
and image and generates any combination of text, audio, and image outputs.
It can respond to audio inputs similarly to human response time in a
conversation.

You can call up ChatGPT with a familiar phrase: "Hey, ChatGPT."

With new real-time conversational speech functionality, you can interrupt

the model, you do not have to wait for a response and the model notices your
emotions.

With real-time translations, ChatGPT-4o acts like a super translator. Talk to

a person in one language and ChatGPT can translate it instantly into another
language. This makes talking to anyone (both speaking different languages)
a breeze! Just what I need for travel to overseas to countries where English is
not a widely spoken language. Personally, this is huge. Having a universal
interpreter in your pocket anywhere around the world is transformative.

Other ways to interact with ChatGPT now include video, so you can share live
footage of, say, a homework math problem you are stuck on and ask for help
solving it. ChatGPT will give you the answer or help you work through it on
your own.

ChatGPT-4o can also perform facial expression analysis. It can look at a

photo and tell you what emotions they are feeling based om their facial
expressions.

ChatGPT-4o is available in the free tier, and to Plus users with up to 5x higher
message limits. OpenAI is rolling out an updated version of Voice Mode with
GPT-4o in alpha within ChatGPT Plus soon.

21
Memory

Remembering what you discuss across all chats saves you from having to
repeat information and makes future conversations more helpful.

As you chat with ChatGPT, you can ask it to remember something specific or
let it pick up details itself. ChatGPT’s memory will get better the more you use
it, and you will start to notice the improvements over time.

For example, you have explained that you prefer meeting notes to have
headlines, bullets and action items summarized at the bottom. ChatGPT
remembers this and recaps meetings this way.

You are in control of ChatGPT’s memory. You can explicitly tell it to

remember something, ask it what it remembers, and tell it to forget
conversationally or through settings. You can also turn it off entirely.

See, Hear, Speak

Voice and image give you more ways to use ChatGPT in your life. Snap a
picture of a landmark while traveling and have a live conversation about what
is interesting about it. When you are home, snap pictures of your fridge and
pantry to figure out what is for dinner (and ask follow-up questions for a
step-by-step recipe). After dinner, help your child with a math problem by
taking a photo, circling the problem set, and having it share hints with both
of you.

Use voice to engage in a back-and-forth conversation with your assistant.

Speak with it on the go, request a bedtime story for your family, or settle a
dinner table debate.

22
Show ChatGPT one or more images. Troubleshoot why your grill will not
start, explore the contents of your fridge to plan a meal, or analyze a complex
graph for work-related data. To focus on a specific part of the image, you can
use the drawing tool in the ChatGPT mobile app.

OpenAI is rolling out voice and images in ChatGPT to Plus and Enterprise
users - voice is coming on iOS and Android (opt-in in your settings) and
images will be available on all platforms.

Analyzing & Creating Charts

ChatGPT-4o is changing data analysis forever.

When analyzing data with ChatGPT, you can create interactive tables and
charts from your uploaded data. You can create at least 12 types of charts or
plots.

1. Line graph
2. Bar chart
3. Pie chart
4. Histogram
5. Scatter plot
6. Box plot (Box-and-Whisker)
7. Heatmap
8. Area chart
9. Radar chart
10. Treemap
11. Bubble chart
12. Waterfall chart

ChatGPT will automatically create an interactive table view, allowing you to

scroll through your data and view all your rows and columns.

23
After uploading a file, you can create interactive charts. ChatGPT can
determine the ideal chart type for the dataset, or you can specify one of their
supported chart types in your prompt.

ChatGPT uses pandas to analyze your data and Matplotlib to create both static
and interactive charts with your data. After using ChatGPT to analyze or
visualize your data, click on the View Analysis link that appears at the end of
the response to see how ChatGPT used these tools.

24
Currently, only bar, pie, scatter, and line charts are interactive in most cases.

You can customize the graphics of your interactive charts and create
summaries explaining your findings.

ChatGPT can also generate multiple charts and analyses in a single prompt.

Analyze attached spreadsheet for Nvidia, ticker NVDA.

Perform technical and statistical analysis on it.
Generate charts and visuals. Show charts only for 2022 to
2024 data.

Everyone knows Nvidia. Let’s use Nvidia (stock ticker: NVDA) stock prices
(you can download the history dataset on Yahoo Finance here by clicking on
the download button) and upload it to ChatGPT.

Submitting the prompt to ChatGPT-4o, it goes through this Technical &

Statistical Analysis process:

1. Data Cleaning and Preparation

2. Statistical Analysis
3. Technical Analysis
25
 4. Visualization

Finally, the charts/plots include:

• Closing Price with Moving Averages

• Volume over Time
• RSI (Relative Strength Index)
• MACD (Moving Average Convergence Divergence) with Signal Line

Closing Prices - NVDA

Volume – NVDA

26
 RSI – NVDA

MACD - NVDA

Straying away from technical analysis, let us try correlating real world events
with stock prices.

Can you correlate these prices (ups and downs) with

significant AI events from the world?

As of this writing (June 2024), the following key trends and milestones
generated by ChatGPT-4o.

27
Let us overlay these milestones onto the price chart.

Write on the chart these events with 2 words for each.

Make sure the words do not overlap.

28
Note: I ran into many errors with ChatGPT-4o not being able to generate the
annotated chart.

It seems there is an issue with plotting the annotations in the current

environment.

Free ChatGPT Users

When using ChatGPT-4o, free users have access to these features:

• Experience ChatGPT-4 level intelligence.

• Get responses from both the model and the web.
• Analyze data and create charts.
• Chat about photos you take.
• Upload files for assistance summarizing, writing, or analyzing.
• Discover and use GPTs and the GPT Store.
• Build a more helpful experience with Memory.

29
Looking Ahead

The next major evolution of ChatGPT has been rumored for a long time. GPT-
5, or whatever OpenAI calls it, their Chief Technology Officer Mira Murati
gave some additional clarity on its capabilities. Murati describes the jump
from GPT-4 to GPT-5 as someone growing from a high-schooler up to
university.

“If you look at the trajectory of improvement, systems like GPT-3 were maybe
toddler-level intelligence. And then systems like GPT-4 are more like smart high-
schooler intelligence. And then, in the next couple of years, we’re looking at Ph.D.
intelligence for specific tasks. Things are changing and improving pretty rapidly.”

Model Intelligence Level

GPT-3 Toddler

GPT-4 Smart High Schooler

GPT-5 PhD (in specific tasks)

GPT-5 may not come out until late 2025 or early 2026.

A recent Bloomberg report that OpenAI is working on a tiered system for

measuring an AI model’s intellectual complexity.

Level 1 Chatbots - AI with conversational language

Level 2 Reasoners - Human-level problem solving

Level 3 Agents – Systems that can take actions

Level 4 Innovators – AI that can aid in invention

Level 5 Organizations – AI that can do all the work of an organization

30
OpenAI's own model, GPT-4 is only at level 1 right now (includes Claude and
Llama). But OpenAI said there are signs that GPT-4 is close to reaching level
2. It allegedly shared some research with employees that shows the model
using reasoning skills that approach human-like capabilities.

Other companies are already working on level 3, models that can perform
multi-step tasks on behalf of humans, like booking an entire vacation or
working through a complicated coding problem on its own. Level 4 models
are “innovators,” who can contribute to new discoveries and inventions. And
finally, level 5 involves entire organizations of AI models making decisions
and working together toward a common goal.

Google Gemini & Project Astra

Google believed that AI was the future of search when it rolled out “AI
Overviews,” previously known as the Search Generative Experience, or SGE -
billions of Google users will see an AI-generated summary at the top of many
of their search results. And that’s only the beginning of how AI is changing
search.

“What we see with generative AI is that Google can do more of the searching for
you,” says Liz Reid, Google’s newly installed head of Search, who has been
working on all parts of AI search for the last few years. “It can take a bunch of the
hard work out of searching, so you can focus on the parts you want to do to get
things done, or on the parts of exploring that you find exciting.”

Google is using its Gemini AI to figure out what you’re asking about, whether
you’re typing, speaking, taking a picture, or shooting a video. It’s using a new
specialized Gemini model to summarize the web and show you an answer. It’s
even using Gemini to design and populate the results page.

OpenAI ChatGPT still does not have that reach – Google is leveraging their
existing hundreds of millions of search users by integrating with Gemini.

31
Rumors are that OpenAI is working on a search feature for ChatGPT that could
make the chatbot a veritable alternative to Google Search. According to
Bloomberg, the company is currently developing the capability, which can
scour the web for answers to your queries and spit out results complete with
citations to their sources. ChatGPT could take information from Wikipedia or
blog posts, for instance, and link to their original pages when you ask it
questions.

Bloomberg says that in one version of the experimental search function,

ChatGPT can show you images along with its written responses whenever
they're relevant. For example, if the chatbot deems illustrated instructions or
diagrams useful for an inquiry, such as "how to change a doorknob" or "how
to clean a split-type AC," then it could include them in its responses. As
Bloomberg notes, ChatGPT can already do searches for paying customers, but
it could give faulty responses or replies with incorrect citations.

Turning Search Online on its Head

Search engines were once your first stop or portal for information - fewer
people are going there because AI Overviews promises to teleport you directly
to where you want to go — minus the grueling drilldowns. Instead of digging
through pages of search results, users will receive specific, detailed answers
directly in the search engine itself.

Direct traffic to websites that rely on clicks and engagement will have to find
other ways to monetize. But it’s a catch 22. Websites might go out of business
resulting in less sources for Google to index information from. SEO may not
work anymore as keywords may not be top priority for AI Overviews. There’s
no easy solution but search engines might need to bear some of the financial
cost.

32
Remember content will still be king. If you create new, fresh, and quality
content for your target audience, you can’t lose. Don’t try to game Google.

There is a major shift in how users will search. Rather than refining your
search (you may go down a rabbit hole and burn hours) if you don’t get the
desired result, you can ask all your questions upfront and get a result in
seconds or faster. You'll end up chatting with Gemini instead.

Gemini will also make Google search better at planning like meal planning
where it lets you specify your tastes and preferences to receive a meal plan
with recipes and a shopping list. And if one part of the plan isn't right, you
can just ask Google search to tweak it until it is something you want to make
and eat.

Gemini will create the plan for you instead of you needing to do the legwork
to search for each recipe and then putting the plan together yourself. Google
expects you to use Search to plan trips, parties, workout routines, and more.
You can use the results elsewhere once you're happy with your plan.

Gemini's multimodal understanding also lets users analyze a live video and
provide answers to a question about it. For example, how to fix a broken arm
on a record player or stuck lever on a camera. Both are instances where you
want to fix something but might not know the make or model of the record
player or camera, or the specific name of the part that isn't working.

Project Astra as the Future of Google AI

33
“We would have this universal assistant. It’s multimodal, it’s with you all the
time.” Call it the Star Trek Communicator; call it the voice from Her; call it
whatever you want. “It’s that helper,” Dennis Hassabis, Google DeepMind.

Project Astra uses Gemini Ultra, and it’s a real-time, multimodal AI assistant
that can see the world, knows what things are and where you left them, and
can answer questions or help you do anything.

Siri and Alexa never managed to be useful assistants. But Google and others
are convinced the next generation of bots is really going to work.

Going forward, Hassabis says, the story of AI will be less about the models
themselves and all about what they can do for you – more like AI Agents. And
that story is all about agents: bots that don’t just talk with you but accomplish
stuff on your behalf.

We’re a few steps closer to the first true AI Agent — a personal assistant that
can plan and make complicated decisions on your behalf. Online searches are
already starting to move in that direction. For instance, if you ask the search
engine for recommendations for nearby hot yoga studios, it will not only give
you a curated list of options but also compile their ratings and other relevant
info.

34
A killer app is a personal assistant that can do things for us in our daily lives
like online grocery shopping, fill out insurance forms, do taxes, and book
your vacation.

A notable feature that ChatGPT-4o does not have yet: keeping track of your
surroundings via video. If you need to ask questions, the AI remembers what
it saw in the video.

Like ChatGPT-4o, it can take in information about your surroundings in real-

time and help you with various tasks, from deciphering code, to spotting your
missing glasses, to guessing which city you’re in. And unlike ChatGPT-4o, it
seems capable of processing video too.

You’ll soon be able to:

• Generate summaries and replies in Gmail.

• Find information and compile timelines from your photos.
• Create charts and analyze data in Google Sheets.
• Get in-depth AI Overviews from search queries.
• Integrate information from across apps (for example, you’ll be able to
build a database with receipts gathered from your Gmail inbox).

Microsoft CoPilot
Microsoft Copilot is an AI-powered assistant designed to enhance
productivity and creativity across various Microsoft applications and
services. Microsoft Copilot aims to transform work by unleashing creativity,
unlocking productivity, and providing intelligent assistance across various
tasks and applications within the Microsoft ecosystem.

35
Integration

Embedded within Microsoft 365 apps like Word, Excel, PowerPoint, Outlook,
and Teams, Copilot enhances productivity by assisting with tasks such as
drafting documents, analyzing data, creating presentations, and
summarizing emails. It leverages user data within the Microsoft ecosystem
to provide personalized assistance.

Functionality

Focuses on productivity within the Microsoft ecosystem, offering features

like real-time code completion (in GitHub Copilot), document
summarization, and task automation. Designed to work seamlessly with
Microsoft Graph by utilizing data from emails, calendars, and documents to
provide context-aware assistance.

Training

Uses foundational large language models (LLMs) tailored to specific tasks

within Microsoft applications. It combines GPT-like models with other
neural network architectures optimized for productivity tasks. The training
data includes document formats, email communication patterns, and
interactions within Microsoft tools.

Personalization
36
Offers deep customization through Copilot Studio, allowing organizations to
tailor the AI assistant to their specific needs, including connecting to other
data sources and automating business processes. It provides personalized
assistance based on user data within the Microsoft ecosystem.

Microsoft positions Copilot as a specialized tool that enhances productivity

and efficiency within its ecosystem, leveraging its deep integration with
Microsoft 365 applications and user data. This makes Copilot particularly
attractive to businesses and individuals who rely heavily on Microsoft
products for their daily tasks.

Apple Intelligence
The next big step for Apple is here. Apple Intelligence is personal intelligence
built into your iPhone, iPad, and Mac to help you write, express yourself, and
get things done effortlessly. All while setting a brand-new standard for
privacy in AI.

Apple Intelligence will be available in beta on iPhone 15 Pro, iPhone 15 Pro Max,
and iPad and Mac with M1 and later, with Siri and device language set to U.S.
English, as part of iOS 18, iPadOS 18, and macOS Sequoia this fall.

37
Apple focuses only on the devices it sells and the personal data that AI could
use. It draws on your personal context while setting a brand-new standard
for privacy in AI.

Apple’s vision for AI isn’t about one big model — it’s a slew of smaller models
that don’t require the same amount of computing power and memory,
running on Apple’s devices and chips themselves. If the AI on the phone
can’t do it, then Apple, or an app using Apple’s tools, reaches out to the cloud
to access a larger AI model.

Here's Tim Cook’s pitch during WWDC for Apple Intelligence.

So, as we look to build in these incredible new capabilities, we want to ensure that
the outcome reflects the principles at the core of our products.

• It has to be powerful enough to help with the things that matter most to you.
• It has to be intuitive and easy to use.
• It has to be deeply integrated into your product experiences.
• Most importantly, it has to understand you and be grounded in your
personal context, like your routine, your relationships, your
communications, and more.
• And, of course, it has to be built with privacy from the ground up.

38
Together, this goes beyond artificial intelligence. It's personal intelligence, and it's
Apple's next big step.

Intelligent Tools

Apple Intelligence powers new Writing Tools, which help you find just the
right words virtually everywhere you write. With enhanced language
capabilities, you can summarize an entire lecture in seconds, get the
condensed version of a long group thread, and minimize unnecessary
distractions with prioritized notifications.

Apple Intelligence enables new ways to express yourself visually. Create fun,
original images and brand-new Genmoji that are personal to you. Turn a
rough sketch into a related image that complements your notes with Image
Wand. And make a custom memory movie based on the description you
provide.

Genmoji opens entirely new ways to communicate, letting users create a new
emoji to match any moment. Emoji are text whereas Genmoji are inline
images.

Supersized Siri

Siri draws on Apple Intelligence for all-new superpowers. With an all-new

design, richer language understanding, and the ability to type to Siri
whenever it’s convenient for you, communicating with Siri is more natural
than ever. Equipped with awareness of your personal context, the ability to
act in and across apps, and product knowledge about your devices’ features
and settings, Siri will be able to assist you like never before.

39
Great Privacy

Apple Intelligence protects your privacy at every step. With Private Cloud
Compute, Apple Intelligence can draw on larger server-based models,
running on Apple silicon, to manage more complex requests for you while
protecting your privacy - data used only for your requests and never stored.

ChatGPT Seamless Integration

With ChatGPT from OpenAI integrated into Siri and Writing Tools, you get
even more expertise when it might be helpful for you — no need to jump
between tools. Siri can tap into ChatGPT for certain requests, including
questions about photos or documents. And with Compose in Writing Tools,
you can create and illustrate original content from scratch.

You control when you use ChatGPT and asked before any of your information
gets shared. Anyone can access ChatGPT for free, without creating an

40
account. ChatGPT subscribers can connect accounts to access paid features
within these experiences.

AI Revenues

Apple's long-term plan for Apple Intelligence is to eventually monetize its

capabilities. While the features of Apple Intelligence will be free to start, the
company aims to make money off the capabilities in the future.

"Apple Intelligence+" is one avenue as a paid subscription service - offering

extra features for a monthly fee, like iCloud. Additionally, Apple will receive a
cut of the subscription revenue from every AI partner that it brings onboard.
By generating revenue from AI services, Apple aims to become less reliant on
hardware tweaks and drive its business through software and artificial
intelligence.

Apple Intelligence Wrap Up

41
The three principles pitched by Tim Cook has positioned Apple to win
eventually:

1. Integration: Apple does vertical integration better than others.

2. Personalization: Apple devices understand 2.2B people better than
others.
3. Privacy: Apple’s brand and business model has more trust (privacy-
first) than others.

Time will tell but Apple is playing the long game.

42
Will AI Take Over Your Job?

People started to see the writing on the wall that their jobs really could be
obsolete. AI will not replace you but by someone who knows AI and does your
job. Everyone should be reskilled and, in some way, have the tools they need
to have to succeed in this new world.

A Goldman Sachs report in March estimated AI will disrupt over 300 million
jobs worldwide. A report from McKinsey estimated that AI will force at least
12 million Americans to find a new job by 2030. The researchers noted that AI
will impact the workforce differently than previous technological
advancements.

A recent [Link] Zeitgeist AI Readiness report shows the positive outcomes

from their generative AI adoption chart.

43
62% of organizations stated improved operational efficiency as the leading
driver behind adopting generative AI. Improved customer experience came in
second at 59%.

Despite growing adoption, there are still many challenges that stall
widespread use of generative AI - respondents cited infrastructure, tooling,
or out-of-the-box solutions not meeting their specific needs.

New Work, New World

According to Cognizant, New Work, New World, Generative AI could deliver
up to $1 trillion in annual growth by 2032, while potentially disrupting up to
90% of existing jobs.

The study also found AI’s significant impact on over half of all jobs driving
the US economy, with a small percentage of workers losing their jobs and
struggling to find new employment.

The study used a model to simulate three levels of AI business adoption —

low, middle, and high — and how those rates could impact jobs and careers.
It looked at 18,000 tasks that the researchers identified as drivers of the US
economy, such as content generation, market analysis, image generation,
reports, and emails. Then, they looked at the impact of generative AI on the
about 1,000 jobs that use these tasks, like management, sales, design, media,

44
and legal positions. The model looked at the percentage of tasks that AI could
automate for each job.

Exposure Score

This score reflects the degree to which generative AI will affect an occupation.
The exposure score considers how many of the job’s tasks could be fully
automated by generative AI; how many it can assist; and the relative
importance of these tasks.

90% of jobs will have at least 5% of their high-value tasks automated by AI.

52% of jobs will have at least 25% of their high-value tasks affected by AI.
About 8% of jobs were at this level in 2023.

The model showed that AI could lead to 9% of the US workforce losing their
job in the next 10 years. What's more, about one out of every nine displaced
workers — about 1% of the total US workforce — will struggle to find new
work after losing their jobs because the skills needed for their current jobs
will not translate to an AI-dominated workforce.

45
Friction Score

High friction score - more challenging to find new work.

Low friction score - easier to find new work.

For example, software developers and database administrators (with high

predicted exposure scores of 8% - bubble 3) have low friction scores of about
40, meaning their journey to new employment is less complicated, likely due
to their in-demand skill set.

In contrast, office, and administrative roles (such as clerical assistants and

receptionists – bubble 17) have a predicted exposure score of 4% but saddled
with a friction score of 80, indicating they will face an uphill battle.

46
Instead of replacing manual labor jobs and "process-centric knowledge
work," like data entry, AI will have a bigger effect on knowledge work, such
as credit analysis, computer programming, web development, database
administration, and graphic design.

According to the study, some of these careers have already seen 50% of their
most important tasks replaced by AI, which could grow to 80% in 10 years.

In a similar June report by McKinsey, it found that high earners could

experience the biggest impact of generative AI automation. This is not all
doom and gloom for workers. Rather, they noted that this is an opportunity
for rethinking skills and training, marking a new phase of employee
development and business strategy.

"As this technology becomes commonplace in the workforce, new employee

skills will be in demand to support areas including business strategy and AI
management," the Cognizant and Oxford Economics authors wrote.
"Reskilling programs, once seen as a tactical add-on to an employee's career
path, will become an essential part of the workday, with time allocated for
training and education."

Preparing for Tomorrow’s Workforce

In a couple of recent reports by McKinsey, AI technology is set to bring about
"12 million occupational transitions" between now and 2030, Kweilin
Ellingrud, a senior partner at McKinsey and director of its Global Institute.
"That's about, give or take, the pace of occupational transitions we had
during COVID."

As people leave shrinking occupations, the economy could reweight toward

higher-wage jobs. Workers in lower-wage jobs are up to 14 times more likely
to need to change occupations than those in highest-wage positions, and

47
most will need additional skills to do so successfully. Women are 1.5 times
more likely to need to move into new occupations than men.

Some areas will see growth, namely roles in healthcare and STEM, Ellingrud
said. About 85% of the jobs that AI will impact, meanwhile, fit into four
categories — administrative assistance, customer service and sales, food
service, and production and manufacturing, according to McKinsey.

Many of those jobs involve repetitive work, data collection, and elementary
data processing, all manageable by automation, according to a McKinsey
report co-authored by Ellingrud. The report estimated that about 11.8 million
workers in roles with shrinking demand will need to move into new lines of
work by 2030.

Technology is one of the critical levers, and generative AI is opening many

possibilities for making knowledge work more productively. When machines
take over dull or unpleasant tasks, more interesting work that requires
creativity, problem solving, and collaborating with others shows up.

Importantly, workers would need to become proficient in using AI—and use

the extra free time to focus on higher-value activities. Leaders can spend
more time on strategic thinking and coaching when they automate more of
their administrative and reporting tasks. Researchers could speed up projects
by relying on automation tools to sort and synthesize large data sets. Writers
can use generative AI to produce first drafts, then spend time refining and
shaping the output.

A perfect example is the evolution of a software developer’s job showing how

generative AI can boost productivity.

48
The future of work, influenced heavily by the rise of AI and automation, will
demand a significant shift in workforce skills. Several key skill areas will be
increasingly important by 2030:

• Technological Skills

o Advanced IT Skills and Programming: There will be a substantial

increase in the demand for advanced IT skills, including
programming and advanced data analysis. This includes skills
related to technology design, engineering, maintenance, and
scientific research.

49
 o Data Analytics: The ability to analyze and interpret complex data
will be critical. This includes both basic data input and advanced
data analysis.

o Digital Literacy: Basic digital skills will become a prerequisite for

all job roles, reflecting the pervasive nature of technology in the
workplace.

• Higher Cognitive Skills

o Critical Thinking and Decision Making: The ability to process

complex information and make strategic decisions will be
increasingly valued.

o Creativity and Innovation: Roles that require creativity, such as

product and UX design, will see increased demand. This also
includes roles that involve critical thinking and complex
information processing.

o Project Management: Managing projects efficiently and

effectively, especially those involving innovative technologies,
will be essential.

• Social and Emotional Skills

o Leadership and Managing Others: As organizations become

more complex, the need for strong leadership and management
skills will grow. This includes skills related to empathy and
interpersonal communication.

o Adaptability and Continuous Learning: The ability to adapt to

new situations and continuously learn new skills will be critical.
This is especially relevant in a fast-evolving technological
landscape.

50
 o Entrepreneurship and Initiative-Taking: Initiative-taking skills
and the ability to take initiative will be important as companies
navigate through continuous disruptions and changes.

• Physical and Manual Skills

o Expect the demand for physical and manual skills to decline

overall, but there will still be a need for these skills in certain
sectors like healthcare, warehousing, and transportation.

The shift towards a technologically advanced workplace will require a

balanced combination of technical proficiency, cognitive capabilities, and
people skills to navigate and thrive in the future work environment.

AI-Driven Societal Transformations

While we focused on the at-risk jobs from emerging technologies, these
shifts, as well as societal changes, usually offer new employment
opportunities as well.

Data from the US Bureau of Labor Statistics Occupational Employment

Projections show that transportation and warehousing is going to be among
the fastest growing sectors over the next decade, with wage and salary
employment in the sector projected to grow 8.6 percent between 2022 and
2032.

At 9.7 percent, the biggest increase in employment is in the healthcare and

social assistance sector, driven less by technological changes and more by
demographic shifts. Due to the ageing population and the growing
prevalence of chronic conditions, the healthcare and social assistance sector
accounts for 2.1 million new jobs by 2032, making up almost half of all new
jobs expected by the end of the projection period.

51
Looking at individual occupations, this trend is also evident, with home
health and personal care aids projected to be by far the fastest-growing
occupation over the next decade, adding more than 800,000 jobs by 2032.
With registered nurses and medical and health service managers also in the
top 10, it’s clear that the health sector is going to be a major driver of
employment growth soon.

As a bonus, throwing in AI expertise, here are some interesting AI job

opportunities in the Home Health industry.

1. AI Health Data Analysts

• Analyze patient data to provide insights.

52
 • Predict health trends and outcomes.

• Optimize care plans based on data analysis.

2. Telehealth Coordinators

• Manage AI-powered telehealth platforms.

• Coordinate virtual appointments.

• Ensure seamless integration of AI tools in telehealth services.

3. Remote Patient Monitoring Specialists

• Monitor patient health using AI-enabled devices.

• Provide real-time updates and alerts to healthcare providers.

• Ensure the accuracy and reliability of monitoring systems.

4. AI-Assisted Rehabilitation Therapists

• Develop personalized rehabilitation programs using AI insights.

• Use AI tools to monitor progress and adjust treatment plans.

• Train patients and caregivers on using AI rehabilitation tools.

5. Virtual Health Assistants

• Provide remote support to patients using AI chatbots.

• Answer health-related queries and provide guidance.

• Assist in managing medication schedules and appointments.

These roles illustrate the diverse opportunities AI creates in the home health
industry, enhancing patient care and improving efficiency.

53
Everybody Loves Andrew
"AI is the new electricity. It will transform and improve all areas of human life."

From Andrew Ng simple guide, ‘How to Build Your Career in AI’, many words
of wisdom (collected insights). The three key steps of career growth are
learning foundational skills, working on projects (to deepen your skills, build
a portfolio, and create impact), and finding a job. Unique elements of an AI
career based on his experience and knowledge in AI diverse industries.

Learning

Learning foundational skills is a career-long process.

AI is nascent, and many technologies are still evolving. While the foundations
of machine learning and deep learning are maturing — and coursework is an
efficient way to master them — beyond these foundations, keeping up to date
with changing technology is more important in AI than fields that are more
mature.

Projects

Working on projects often means collaborating with stakeholders who lack

expertise in AI.

This can make it challenging to find a suitable project, estimate the project’s
timeline and return on investment, and set expectations. In addition, the
highly iterative nature of AI projects leads to special challenges in project
management: How can you produce a plan for building a system when you
don’t know in advance how long it will take to achieve the target accuracy?
Even after the system has hit the target, further iteration may be necessary to
address post-deployment drift.

Job

Inconsistent opinions on AI skills and jobs roles.

54
While searching for a job in AI is like searching for a job in other sectors, there
are also major differences. Many companies are still trying to figure out
which AI skills they need, and how to hire people who have them. Things
you’ve worked on may be significantly different than anything your
interviewer has seen, and you’re more likely to have to educate potential
employers about some elements of your work.

Who Will AI Replace Next?

The demand for digital freelancers, particularly in writing and coding, has
declined by 21% since the launch of ChatGPT in November 2022, according to
research conducted by Imperial College Business School, Harvard Business
School, and the German Institute for Economic Research.

The research paper, titled “Who is AI Replacing? The Impact of Generative AI

on Online Freelancing Platforms,” investigates the influence of generative AI
technologies on the demand for creative professionals who work on an hourly
basis for various clients. The study analyzed data from a global online
freelancing platform, covering almost two million job postings across 61
countries over a two-year period from July 2021 to July 2023.

The researchers categorized the job roles into three sectors: automation-
prone, manual work, and image generation. They tracked the frequency of
job postings throughout the two-year period to understand the demand for
freelancers and ChatGPT’s influence.

The study found that since ChatGPT’s launch, the number of job postings
related to writing, software, app and web development, and engineering
(automation-prone jobs) had decreased by 21% compared to the pre-
ChatGPT period. Freelance jobs in data entry, video and audio editing, and
social media post-production were slightly less affected, with a 13% drop.
Meanwhile, jobs focused on image generation, such as graphic design and 3D

55
modelling, saw a 17% decline in demand after the introduction of image-
generating AI tools.

Latest Upwork research on generative AI reflects a skills-biased technology

change happening, where freelancers who work with this technology
generate higher earnings and higher-complexity, higher-value work by
leveraging a new set of skills. It is part of the reason Upwork foresee a theme
of job transformation this year, as their research has found AI is unlikely to
replace most jobs but will certainly change the tasks and skills required for
the workforce to generate value.

Not only are these skills in demand, but they also add value to the future of
work. Professionals who work with these AI-based technologies generate
higher earnings and undertake higher-complexity, higher-value work by
leveraging a new set of skills.

56
57
The Massive Reach of ChatGPT

The focus here is general usage by users, not industries – we’ve covered some
of that in the previous chapter. But we do cover usage by employees in their
workplace.

Since its launch in November 2022, ChatGPT has experienced explosive

growth. It reached 1 million users within just five days and had over 100
million monthly active users by January 2023. By mid-2024, the user base
had grown to over 180 million. The platform's popularity is evident from its
peak monthly visits of 2 billion in April 2024, although this has since
decreased to around 600 million visits per month. The ChatGPT app has also
seen significant traction, with over 110 million downloads across iOS and
Android platforms.

From the latest Pew Research report on the use of ChatGPT, adults under 30
stand out: 43% of these young adults have used ChatGPT, up 10 percentage
points since last summer. Use of the chatbot is also up slightly among those
ages 30 to 49 and 50 to 64. Still, these groups remain less likely than their
younger peers to have used the technology. Just 6% of Americans 65 and up
have used ChatGPT.

58
There are three potential reasons Americans might use ChatGPT:

1. for work,
2. to learn something new,
3. for entertainment.

59
The share of employed Americans who have used ChatGPT on the job
increased from 8% in March 2023 to 20% in February 2024, including an 8-
point increase since July.

60
to U.S. adults overall, about one-in-five have used ChatGPT to learn
something new (17%) or for entertainment (17%). These shares have
increased from about one-in-ten in March 2023.

Use of ChatGPT for work, learning or entertainment has risen across age
groups over the past year. Still, there are striking differences between these
groups (those 18 to 29, 30 to 49, and 50 and older).

For example, about three-in-ten employed adults under 30 (31%) say they
have used it for tasks at work – up 19 points from a year ago, with much of
that increase happening since July. These younger workers are more likely
than their older peers to have used ChatGPT in this way.

Adults under 30 also stand out in using the chatbot for learning. And when it
comes to entertainment, those under 50 are more likely than older adults to
use ChatGPT for this purpose.

61
ChatGPT: Going Mainstream
I use ChatGPT every day. I have already shifted away from Google Search as
my go-to starting portal for information.

Obviously, it is very annoying when I need go to the OpenAI website on my

desktop or web browser or open my mobile app. Just need it as easily
accessible as possible.

ChatGPT is available on a desktop, only for MacOS (version 14+ with Apple
Silicon M1 or better), just not Windows yet – later this year.

Chat about email, screenshots, files, and anything on your screen. It

seamlessly integrates with how you work, write, and create. And best of it,
fast access to ChatGPT - ‘Option + Space’ opens ChatGPT from any screen on
your desktop!

62
Power users will share my biggest complaint - searching conversations! The
mobile app has it but not the web version... yet.

63
Unlocking Retrieval-Augmented
Generation

Large language models don’t contain the company-specific information that

your employees or customers may be looking for. Enter RAG. Retrieval-
Augmented Generation (RAG) is a technique in artificial intelligence,
especially within natural language processing, where a system combines
information retrieval with text generation to produce accurate and detailed
responses.

Definition

RAG is an architectural approach that combines the strengths of retrieval-

based methods and generation-based methods to improve the performance
of large language models (LLMs). It involves retrieving relevant information
from external data sources and using this information as context to generate
more accurate and contextually relevant responses.

RAG involves two main steps:

1. Retrieval: The AI system first searches a large database or collection of

documents to find relevant information related to the query or topic at
hand - like a search engine, where it pulls up relevant articles,
documents, or data.

2. Generation: Using the information retrieved, the AI then generates a

response. It crafts a coherent and contextually appropriate answer by
synthesizing the retrieved information.

Step 1

When presented with a question or query to the AI, it doesn’t rely solely on its
pre-existing knowledge (e.g., ChatGPT-4o). Instead, it actively searches for

64
additional information from external sources, such as online databases,
documents, or knowledge bases.

Step 2

After gathering the relevant information, the AI uses this data to formulate a
detailed and accurate response, combining the newly retrieved information
with its inherent language generation capabilities.

Retrieval-Augmented Generation is a powerful approach that combines the

strengths of large language models and information retrieval systems,
enabling AI to provide more accurate, up-to-date, and context-relevant
responses.

To RAG or Not to RAG?

Here are the pros and cons of RAG. Decide for yourself based on your situation
whether to use RAG or not – do the pros outweigh the cons or vice-versa?

Pros of RAG

• Improved accuracy and factual correctness: By incorporating external

data, RAG can provide more accurate and factually correct information,
overcoming the limitations of the fixed training data in traditional
language models.

• Access to up-to-date knowledge: RAG can retrieve the latest

information from constantly updated data sources, ensuring the AI's
knowledge remains current and relevant.

• Context-specific responses: The retrieval component allows RAG to

tailor its responses to the specific context and domain of the query,
providing more relevant and useful information.

65
 • Scalability and adaptability: RAG can be adapted to work with any
domain-specific data source, making it highly scalable and versatile
across different applications.

Cons of RAG

• Retrieval quality dependence: The performance of RAG heavily relies

on the quality and relevance of the retrieved information. Inaccurate or
irrelevant retrieval can lead to suboptimal or incorrect outputs.

• Computational overhead: The additional retrieval step can increase

computational requirements and latency, potentially slowing down the
generation process.

• Data curation challenges: Ensuring the quality, trustworthiness, and

lack of biases in the external data sources used for retrieval can be a
significant challenge.

• Interpretability issues: While RAG provides more transparency by

linking outputs to retrieved information, fully explaining the
reasoning behind the AI's decisions remains a challenge.

• Knowledge scope limitations: RAG limited the scope of information

available in its external data sources and may struggle with tasks
requiring knowledge beyond those sources.

RAG vs. Transfer Learning: What’s the

Difference?
Retrieval-Augmented Generation (RAG) and transfer learning are related
concepts in the field of machine learning, but they are not the same.

Transfer learning is a machine learning technique where a model trained on

66
one task is adapted to perform a different but related task. It leverages the
knowledge gained from the initial training to improve performance on the
new task.

Similarities

Both RAG and transfer learning aim to improve the performance of machine
learning models by leveraging existing knowledge. Also to adapt models to
specific tasks or domains.

Differences

Purpose: RAG focuses on enhancing the generation capabilities of LLMs by

incorporating external information, while transfer learning focuses on
adapting a pre-trained model to a new task.

Mechanism: RAG involves a retrieval step to fetch relevant information,

whereas transfer learning involves fine-tuning a pre-trained model on a new
dataset.

Application: RAG is particularly useful for tasks requiring up-to-date and

context-specific information, while transfer learning is useful for a wide
range of tasks where pre-trained models can be adapted to new tasks.

While both RAG and transfer learning are powerful techniques in machine
learning, they serve different purposes and operate through different
mechanisms. RAG is not just transfer learning; it is a hybrid approach that
combines retrieval and generation to enhance the capabilities of LLMs in
providing accurate and contextually relevant responses.

RAG vs. LLM: A Comparative Look

Retrieval-Augmented Generation and large language models (LLMs) are both

67
advanced techniques in natural language processing, but they have distinct
characteristics and functionalities.

Knowledge Source

LLMs: Traditional LLMs like GPT-3 rely solely on their limited trained data.
This training data is static and does not include information beyond the
model's cut-off date. As a result, LLMs can generate responses based only on
the knowledge embedded during their training phase.

RAG: RAG enhances LLMs by incorporating a retrieval mechanism that

fetches relevant information from external, dynamic data sources. This
allows RAG to access up-to-date information and provide more accurate and
contextually relevant responses.

Accuracy and Reliability

LLMs: While LLMs can generate coherent and contextually appropriate text,
they are prone to "hallucinations" where they produce factually incorrect or
nonsensical information. This is because they do not have a mechanism to
verify the accuracy of the information they generate.

RAG: By retrieving information from authoritative sources, RAG significantly

reduces the likelihood of hallucinations. The cross-referenced retrieved data
makes the generated responses more accurate and dependable.

Contextual Relevance

LLMs: The responses generated by LLMs are based on patterns learned

during training. They may not always be contextually relevant, especially if
the query pertains to recent events or specific domain knowledge not covered
in the training data.

68
RAG: RAG systems can dynamically retrieve and integrate context-specific
information from external sources, ensuring that the responses are highly
relevant to the user's query. This is particularly useful for applications
requiring up-to-date or domain-specific knowledge.

Transparency and Traceability

LLMs: Traditional LLMs do not provide transparency regarding the sources

of information they generate. This lack of traceability can be problematic in
applications where source verification is crucial.

RAG: RAG allows for the inclusion of source citations in the generated
responses. This transparency enables users to trace back the information to
its original source, enhancing trust and credibility.

Flexibility and Adaptability

LLMs: Updating the knowledge base of an LLM requires retraining the model
with new data, which is a resource-intensive process. This limits the model's
ability to adapt quickly to current information.

RAG: Update RAG frameworks by modifying the external data sources they
retrieve from. This makes RAG systems more flexible and adaptable to
current information without the need for extensive retraining.

Use Cases and Applications

LLMs: Use LLMs for general-purpose text generation, language translation,

summarization, and other tasks that do not require real-time access to
external information.

RAG: RAG is particularly useful in applications where up-to-date, accurate,

and context-specific information is critical. Examples include healthcare
information systems, business intelligence, customer support, and internal
knowledge base management.

69
The unique aspect of Retrieval-Augmented Generation lies in its ability to
combine the generative capabilities of LLMs with the retrieval of relevant,
up-to-date information from external sources. This constructive
collaboration addresses many of the limitations of traditional LLMs, such as
hallucinations, outdated knowledge, and lack of transparency, making RAG a
powerful tool for a wide range of applications.

Is RAG the Holy Grail of Enterprise AI?

While RAG offers significant advantages and has the potential to transform
many aspects of enterprise AI, it’s important to recognize both its strengths
and limitations.

RAG is a powerful tool in the enterprise AI toolkit, offering distinct

advantages in accuracy, relevance, and personalization. However, it is not a
panacea. It complements other AI technologies and choice is based on the
specific requirements of the application, but it certainly represents a
significant advancement in the capabilities of AI systems.

RAG’s potential for transforming various industries, including customer

service, e-commerce, healthcare, and more is enormous. A few possible
scenarios:

• Personalized Product Recommendations (eCommerce)

o RAG can provide highly personalized product recommendations

by integrating real-time data from various sources such as
product catalogs, customer reviews, browsing patterns, and
external market insights. This allows e-commerce platforms to
offer tailored suggestions that align with a customer's unique
preferences and interests.

70
 o Example: If a customer frequently browses camping equipment,
RAG can recommend complementary products like a lightweight
tent, or a high-performance sleeping bag based on the latest
product releases and market trends. It can also incorporate
external data such as weather forecasts to suggest appropriate
gear for upcoming trips.

• Automating Routine Inquiries (Customer Support)

o RAG can streamline customer support processes by automating

responses to common and repetitive queries. This frees up
human agents to focus on more complex and intricate customer
interactions.

o Example: A customer support system using RAG can manage

routine inquiries about account information, order status, and
basic troubleshooting, allowing human agents to address more
nuanced issues.

• Clinical Decision Support (Healthcare)

o RAG can retrieve the latest research, clinical guidelines, and

patient data to provide healthcare professionals with up-to-date
information to aid in diagnosis and treatment decisions.

o Example: A doctor enters symptoms and medical history, and the

system retrieves relevant case studies and treatment options.

• Content Generation (Publishing)

o RAG can retrieve relevant data, research, and historical context

to assist authors and journalists in generating well-researched
articles, books, or reports.

o Example: A journalist writing about climate change retrieves the

latest studies and generates a comprehensive article with cited

71
 sources.

• Customer Insights (Marketing)

o RAG can retrieve data from customer surveys, social media, and
purchasing behavior to generate insights and trends to inform
marketing strategies.

o Example: A marketer retrieves data on customer preferences and

generates a report highlighting key trends and potential areas for
campaign focus.

By leveraging Retrieval-Augmented Generation, various industries and

sectors can improve the accuracy, relevance, and personalization of their
information and services. This technology not only enhances efficiency but
also provides a competitive edge by enabling more informed decision-
making and better user experiences.

Amazon’s AI Secret Weapon

From a recent Business Insider article, Amazon is secretly working on a
ChatGPT killer. The secret internal project code-named "Metis," named after
the Greek goddess of wisdom, is a new service accessible through a web
browser, like other AI assistants.

Powered by an internal Amazon AI model called Olympus, it is a more

powerful version of the company's publicly available Titan model, according
to those familiar with the project.

At its core, Metis provides text- and image-based answers in a smart,

conversational manner, according to the internal document. It can also share
links to the sources of its responses, suggest follow-up queries, and generate
images.

72
Amazon wants Metis to use RAG, meaning it can retrieve information beyond
the data originally used to train its Olympus model. This aims to generate
more up-to-date responses. For example, Metis should be able to provide the
latest stock prices, unlike some other chatbots that don't use RAG.

Metis can also function as an AI agent, one of the sources said. AI agents can
automate and perform complex tasks based on existing data, such as creating
a vacation itinerary. Metis' potential uses could include turning on your lights
or booking a flight for you.

73
Who’s Leading the AI Patent Race?

We will touch on AI patents here as it gives an indication on what direction

and where innovation is heading. More importantly, why this matter:

• Technological Leadership: Patents are a strong indicator of a country's

or company's technological leadership and innovation capacity.
Leading in AI patents suggests a strong position in the future
technology landscape, which can influence various sectors, from
healthcare to defense.

• Economic Impact: AI technologies have the potential to revolutionize

industries, improve productivity, and create new economic
opportunities. Countries that lead in AI patents are likely to have a
competitive edge in the global economy, attracting investments and
fostering job creation in high-tech sectors.

• National Security: AI technologies have significant implications for

national security, including military applications and cybersecurity.
Dominance in AI patents can translate into superior capabilities in
these critical areas, giving leading countries a strategic advantage.

• Global Influence: Technological leadership in AI can enhance a

country's global influence, enabling it to set standards and shape the
direction of future technological developments. This can have long-
term geopolitical implications, affecting international relations and
power dynamics.

• Intellectual Property and Legal Influence: Owning many AI patents

allows a country or company to exert influence over the development
and use of AI technologies globally. It can lead to a dominant position
in licensing and cross-licensing agreements, potentially affecting the
competitive landscape in various industries.

74
The chart below shows the number of AI-related patents granted each year
from 2010 to 2022. These figures come from the Center for Security and
Emerging Technology, accessed via Stanford University’s 2024 AI Index
Report.

Reference: [Link]
1116

75
China first overtook the U.S. in 2013, and since then, has seen enormous
growth in the number of AI patents granted.

In the U.S., IBM, Microsoft, and Google has the lion share of AI patents. In
China, AI patenting is more distributed across tech firms (e.g., Baidu,
Tencent), government organizations, and universities.

According to recent Patent Landscape Report on Generative AI from the

United Nations World Intellectual Property Organization (WIPO), China is
currently leading the global race for generative AI patents by a significant
margin.

• China filed over 38,000 generative AI patents between 2014 and 2023.

• This is approximately six times more than the United States, which
filed 6,276 patents during the same period.

76
 • Chinese companies dominate the top 10 list of generative AI patent
applicants, occupying six spots.

• Tencent, Ping An Insurance Group, and Baidu are the top three
companies globally in terms of generative AI patent holdings.

The patent filings cover various applications of generative AI, including:

• Video and image-related inventions (leading category)

• Text applications

• Speech and music applications

While China's lead in patent numbers is substantial, experts caution that

quantity doesn't necessarily equate to quality or impact of innovations.
Factors to consider include:

• Many patents may represent incremental advancements rather than

groundbreaking innovations.

• State subsidies and policies in China may influence patent filing

numbers.

• A comprehensive evaluation of innovation ecosystems should include

factors beyond patent counts, such as startup activity and
commercialization rates.

It's worth noting that generative AI patents currently account for only 6% of
all AI patents globally, but the field is experiencing rapid growth. The
number of generative AI patents has increased eightfold since 2017, with over
a quarter of all generative AI patents published in 2023 alone.

While China leads in patent numbers, the global AI landscape remains

competitive, with significant contributions from other countries like the
United States, South Korea, Japan, and India.

77
AI Revolutionizing the Travel
Industry

In a Feb 2024 Travel Sentiment Study Wave 82 (Longwoods International and

Miles Partnership) on American travelers, only 14% of them have used
ChatGPT to plan a trip in the past six months. And only 31% of them report
that it is likely they will use ChatGPT to plan their next trip.

78
Also, in a recent MoneyLion (May 2024) Travel & AI Trends report:

• Seven in ten Americans (70%) are either using, planning to use, or

open to using AI to plan their trips this year.
• One in five younger adults (18-34) say they are already integrating AI
into their travel plans (20%), while only 2% of the 65+ group are
currently using AI for travel purposes.
• 81% of Americans with children under 18 living in household are using,
plan to use or have used AI to plan a trip.

AI is revolutionizing travel planning, with a significant majority of

Americans willing to leverage this technology. Younger generations are
leading this charge (81% of 18 to44 year olds are using/planning/would use
AI to plan travel this year, compared to only 55% of those 55+), indicating a
potential shift towards more tech-driven travel experiences and reshaping
travel services.

79
How Travelers Are Embracing AI
Manually planning a trip could take hours, days, and even weeks or months
depending on the trip length and destinations involved.

Travel is a good case study. It’s one of the top five categories of paid search
advertising, according to Morgan Stanley analyst Brian Nowak, and Google
search is the first stop for travel planning on the internet.

Based on the user’s prompt, Google Gemini AI model will now research
publicly available information as well as tap into specific details like flight
times and hotel bookings to work up a custom, multiday vacation itinerary
“in a matter of seconds.”

Google recently demonstrated a travel tool at their I/O Developer Conference

that will draw on all the company’s data on flights, hotels, local attractions,
and weather—not to mention your Gmail—to plan and map out itineraries.
If popular, such travel tools would create new placements for the search ads
that bring Alphabet $200 billion a year.

Google is billing its Gemini model as offering something more than other
chatbots by combining publicly available information with personal details
like someone’s inbox. With information from the user’s email, Google Maps,
and Gemini, an itinerary of flights and hotel details built with ‘personal’
information is much more relevant and valuable.

Fifty-six percent of travelers use AI for locating restaurants, 53% for hotel
recommendations, and 51% for local transportation recommendations. It
means that conventional booking sites might need to start incorporating AI
features if they want to stay relevant and competitive.

Some travelers say they’ve found the most success by inputting their
preferences into several AI-powered travel sites, then selecting from each of
their responses to create one ultimate itinerary.

80
Meanwhile online travel agent Expedia was showing off an AI travel assistant
it calls Romie to a Las Vegas gathering of business partners. Built with
OpenAI’s ChatGPT, Romie can plan trips and pop into group text chats with
useful updates about flight changes. You can try it by visiting Expedia’s EG
labs website with your iPhone.

[Link] has an AI trip planner that’s also built on the OpenAI platform,
with variants at its other websites like Priceline.

There are a lot of AI travel experiments out there.

“The runway is pretty crowded,” says Natalie Bowman, a product manager at

Alaska Airlines who’s built AI travel tools for the carrier with both Microsoft’s
version of ChatGPT and Google’s Gemini.

Its ChatGPT-based helper, Alaska Inspire, answers spoken or written

questions—even complicated ones like “Which flights to Europe can I buy
with my frequent-flier miles?” The airline wants to see if the tool’s ease-of-
use turns more searches into bookings. It may also increase revenue per user
by finding flights that are more suitable, but not necessarily the cheapest.

This summer, Alaska Airlines will roll out a more sophisticated tool that uses
Google’s AI. Features setting it apart from OpenAI’s offering include
interactive maps, immersive photos, and timely events at travel destinations.
Google’s latest version promises to let a traveler use a photo, video, or a piece
of music to find associated places.

Actionable Travel Recommendations with AI

Mindtrip is an AI powered platform that empowers everyone to travel
differently. Combining conversational AI with the rich and visual world of
travel content, Mindtrip is the first travel platform in the market to cater to
the fluid ways consumers travel.

81
Whether you're a meticulous planner arranging flights and accommodations,
a parent in search of family-friendly activities, an intrepid explorer seeking
hidden gems, or someone craving an authentic local dining experience on a
whim, Mindtrip simplifies the entire travel process. From planning and
scheduling to booking and on-the-ground exploration, Mindtrip offers a
comprehensive solution, consolidating all essential travel resources into one
visually stunning platform.

Designed to inspire users by advanced AI technology, users simply visit the

site, fill out a brief travel persona quiz, and start chatting with Mindtrip's
conversational AI. Conversations can cover a wide range of topics, from
general inquiries like "Where is the best place to scuba dive nearby?" to more
specific questions such as "What are the must-see attractions for my family on
the Big Island in Hawaii?" or "Which destinations are ideal for a remote
proposal?" Utilizing its vast database of places sourced from over 30
countries, Mindtrip swiftly processes this information. Within seconds, it
generates a tailored, practical, and inspiring travel itinerary.

Useful & Relevant Information

82
Featuring streamlined recommendations for everything travelers need,
including the best flights, restaurants, cool boutique hotels, must-see
attractions, and driving distances, Mindtrip's itinerary is fully editable,
empowering travelers to jump in and easily move things around.

Inspired or discover another Mindtripper's post? You can copy and customize
your itineraries or save proposed ideas to your favorites, where you can
contemplate them and book later.

Sharing with Travel Group

Unlike other platforms, Mindtrip also empowers users to invite anyone they
are traveling with, like family and friends, to weigh in and help co-create an
itinerary. Throughout the process, Mindtrip will highlight incredible photos,
maps, review summaries, reservation options, and real-time pricing, so that
users can gain a full view into their upcoming trip.

Real-Time Dynamic Planner

While on their trip, users can reference what's up next each day, including
any ticket information stored on the platform. Post-trip, users can even use
the platform to track expenses, scrapbook their adventure, and publish it, so
others in the Mindtrip community can become inspired.

Mindtrip makes travel planning and recommendations actionable,

customizable, and shareable – all in a single place.

83
 Source: Ark Investment Midjourney

Travel Experts Weigh In on ChatGPT

Travel leaders have already had to integrate personalized marketing,
predictive pricing, deep analytics, and ecommerce into the way they do their
work. But generative AI is adding powerful new capabilities in all these areas,
not to mention new ones that are exponentially more impactful.

Generative AI won't displace travel agents; instead, it will enhance their

efficiency, enabling them to focus on crafting tailored experiences that
resonate with travelers on a deeper level.

Daniel Levine (visionary, industry trends expert, keynote speaker) believes

generative AI tools tend to do best when it comes to information that’s static,
like sightseeing. Levine says AI chatbots have been misleading when replying
to queries like “list hotels in Tokyo with 2-bedroom suites,” even offering up
84
out of business properties. “For trip planning it's best to think of ChatGPT as
a tool rather than a travel agent,” says Levine. “You have to spend time with
it to massage its answers.”

SEO Travel found that ChatGPT’s travel suggestions often send people to
places that don’t exist, fall short of logistical planning, or suggest restaurants
and attractions outside of operating hours.

Travel professionals already have experience, contacts and knowledge about

local travel details that can make or break a trip or turn a good trip into a
memorable, once-in-a-lifetime experience. Add in the power of generative
AI, and they become industry leaders when it comes to tailoring individual
trips for their clients. This technology makes it easy for them to broaden their
reach – unmatched by larger travel companies or new travel technology
startups. This also allows them to pivot much more quickly to new market
demands.

Moreover, employees in travel companies tend to be innovators by nature.

Their first instinct is usually to create something that adds value to
customers in amazingly powerful ways. They also understand once travel
preferences change, customers simply don't want to go back to the old way of
doing things.

Alex Goryachev (award-winning AI & innovation executive) sums it up nicely.

“Imagine a world where travel planners have more time to listen,

understand and cater to the dreams of each traveler, then make every
journey special and unique. AI provides the tools and insights, but it's the
human touch, the passion and the creativity of travel planners that turn trips
into cherished memories. Far from taking jobs, AI will open new doors for
travel planners, allowing them to shine brighter and make a deeper impact
on the lives of those they serve.”

85
Here’s a useful ChatGPT travel cheat from these travel professionals - learn
basic expressions in a foreign language.

Make a list of [number] expressions to help navigate

[country].

For example:

Make a list of 10 expressions to help navigate Malaysia.

ChatGPT-4o gave us these:

1. Selamat pagi - Good morning

2. Selamat petang - Good evening
3. Tolong - Please
4. Terima kasih - Thank you.
5. Maaf - Sorry / Excuse me
6. Berapa harganya? - How much does it cost?
7. Di mana tandas? - Where is the toilet?
8. Saya tidak faham - I don’t understand.
9. Boleh saya dapatkan menu? - Can I get the menu?
10. Tolong tunjukkan jalan ke... - Please show me the way to...

These expressions cover basic greetings, polite phrases, and essential

questions for getting around.

86
The Ultimate Trip Planner with AI
Here is a peek into the future of what AI travel planning looks like. We start
off spending a few minutes with setting up our Travel Persona and then
asking Mindtrip to plan a 4-day vacation in November to Penang Island in
West Malaysia.

87
After finishing my travel persona, here is what kind of traveler Mindtrip
thinks I am (feel free to edit your travel persona if not accurate).

In seconds Mindtrip generates a tailored, bookable itinerary that is editable

and shared with family and friends.

88
Mouse over some of the properties (like hotels, attractions, restaurants) and
you’ll get detailed information when available. Or book an attraction or stay
at the hotel.

89
Here’s a Calendar view.

Travel is fluid - you might book parts of your trip today and then over the
course of months, add things with whatever inspires you and want to change
it or edit it.

90
During travel, you should be able to see what’s happening the following day
according to your itinerary, with ticket information and more stored in
Mindtrip.

After your travel, use Mindtrip to track expenses, scrapbook your travels and
publish or share about your experiences for others to see within the Mindtrip
community.

All in one place. That’s the future of AI trip planning and travel.

91
The Rise of AI Computers

Johanna Stern from the Wall Street Journal coined the term, ‘AI-puter.’

AI-puter (noun): A computer designed to execute AI tasks better than older,

non-AI computers.

Microsoft's Copilot+ PCs are a new line of Windows computers designed

specifically for artificial intelligence. These PCs offer better performance,
longer battery life, and advanced AI features, providing real competition to
Apple's M-powered MacBooks.

Microsoft achieved this by making two significant changes:

1. Optimizing Windows for Qualcomm's latest chips - these chips are like
those in smartphones, offering all-day battery life, cooler
temperatures, and fast performance.
2. Introducing a new chip component that enhances AI capabilities
directly on the laptop. This means there's no need to rely on cloud
processing for AI tasks.

Inside Microsoft Hardware Innovations

Setting these AI computers apart is Microsoft new AI hardware and software.

• ARM Chips: Current Windows laptops have Intel or AMD chips based
on the old x86 architecture. The new Copilot+ PCs use Qualcomm
Snapdragon X series chips based on the more efficient ARM
architecture. Apple made a similar switch to ARM chips for its Macs a
few years ago, leading to quieter, cooler, and longer-lasting laptops.
• NPUs (Neural Processing Units): In addition to the CPU and GPU, these
computers now have NPUs, which are specialized for handling complex
AI tasks directly on the laptop.
92
 • Edge Computing: Traditionally, AI processing happens in the cloud (at
a data center). With NPUs, some AI processing can happen right on your
computer, making it faster and more secure. Copilot+ PCs come with
over 40 on-device AI models, including small language models for
generative AI. However, for larger language models like ChatGPT or
Microsoft's Copilot, you need to connect to the Internet.

Microsoft Software: The AI Edge

The NPUs do all the heavy-duty processing.

• Recall: This feature constantly captures what's on your screen and uses
an on-device AI model to process and search it. You can control which
apps or websites it captures from or turn it off entirely.
• Live Captions: Like features on other AI devices, this provides real-
time translation of 44 languages into English. Built into Windows, it
works with any video call or app including in-person conversations.
• Cocreator: As you draw in Microsoft Paint, AI generates an image based
on your sketch. For example, if you type a prompt like "A Windows XP
wallpaper with a mountain and sky," and start drawing, an AI image
will appear alongside your sketch, updating as you change colors.

These tools are just the beginning. Developers can create their own on-device
AI software to take full advantage of the NPU's capabilities.

93
The Microsoft Prompting Playbook
Microsoft Prompting Playbook – just ASK.

Generative AI tools like Microsoft Copilot can boost your creativity, enhance
your productivity, assist with research, and save you time. You don't need to
be a computer scientist to benefit from it. Just follow three simple steps to
give Copilot instructions, known as prompts, making it as easy as ‘ASKing’
for what you need: Ask, Specify, and Keep Refining.

Action (A)

Explain what you want Copilot to do. Clearly state what you need help
with.

Style (S)

Describe the format you want the response presented in. Provide
specific details to refine the request.

Key details (K)

Set the stage with more context about your situation. Review the results
and adjust, as necessary.

An example from Microsoft follows:

Action

“I need help with scheduling 15 minutes of daily mindfulness

time, please.”

Style

“For each day of the week, please include daily prompts to help
me get started with meditating and journaling.”

94
Key details

“I am a nature enthusiast who loves spending time in the park.”

Putting it together:

“I need help with scheduling 15 minutes of daily mindfulness

time, please. For each day of the week, please include daily
prompts to help me get started with meditating and journaling.
I am a nature enthusiast who loves spending time in the park.”

While including Action, Style and Key details will help you get more useful
results, it doesn’t matter in what order you ASK for help — Copilot will
understand. You can mix these elements up any way you like as you craft your
prompts, telling them about your situation first, or even starting with the
format you want for your results.

It’s a big step toward AI-first devices. Until recently, AI features are an
afterthought and tacked onto devices at the end. Those days are now behind
us. Major manufacturers like HP, Acer, Dell, and Lenovo, are planning to soon
release AI PCs of their own, and AMD and Intel are working on AI-specific
chips.

As AI features become more valuable, the increasing demands they place on

our devices, from phones to desktops, might shorten the time we keep them.

Carolina Milanesi, President of Creative Strategies, predicts that the

replacement cycle for PCs might every two to three years instead of every six,
a change the industry hasn't seen in decades. This could also raise the average
selling prices for new PCs since those with AI capabilities are more expensive.
This trend might extend to smartphones, potentially reversing the global
slump in sales.

95
 “Remember that generative AI is not once and done. You’re going to
continue to push compute, and build models that are larger, and so you will
have to continue to upgrade devices in order to keep up with the pace of
generative AI.”

Exploring Small Language Models (SLM)

Microsoft introduced the Phi-3-mini, a 3.8 billion parameter language model
trained on 3.3 trillion tokens, whose overall performance, as measured by
both academic benchmarks and internal testing, rivals that of models such as
Mixtral 8x7B and GPT-3.5 (e.g., phi-3-mini achieves 69% on MMLU and 8.38
on MT-bench), despite being small enough to be deployed on a phone.

The innovation lies entirely in their dataset for training, a scaled-up version
of the one used for phi-2, composed of heavily filtered web data and synthetic
data - robustness, safety, and chat format.

Thanks to its small size and quantized to 4-bits, phi-3-mini only takes up
about 1.8GB of memory. Microsoft evaluated this quantized model by
deploying phi-3-mini on an iPhone 14 with an A16 Bionic chip, running
natively on-device and fully offline, achieving more than 12 tokens per
second.

Running AI models locally on a smartphone, laptop, or PC reduces the delays

and outages that can happen when queries go to the cloud. This ensures that
your data stays on your device and can enable new AI applications that
weren't possible with a cloud-centric model, such as AI apps deeply
integrated into a device's operating system. Apple Intelligence?

96
AI Agents: The Future Workforce

An AI agent is a software program or system designed to perform tasks

autonomously by perceiving its environment, making decisions, and taking
actions to achieve specific goals. Think of AI agents as digital assistants that
can automate processes, make intelligent decisions, and interact with their
surroundings without constant human intervention.

Key Components of Powerful AI Agents

• Perception: AI agents gather information from their environment
using sensors or data inputs. For example, a chatbot might receive text
messages, while a self-driving car uses cameras and radar.
• Decision-Making: Based on the information collected, AI agents use
algorithms or models to decide the best course of action. This agent
function decision-making process maps percepts (sensory inputs) to
actions.
• Action: Once you make your decision, AI agents execute actions using
actuators. In software, this could be sending a message or updating a
database, while in physical systems, it could involve moving a robotic
arm or steering a vehicle.

Different Types of AI Agents Explained

AI agent types are based on their complexity and capabilities:

• Simple Reflex Agents: These agents respond directly to specific stimuli

in their environment without considering the history of their
interactions. They operate on a condition-action rule, like a thermostat

97
 that turns on the heat when the temperature drops below a certain
point.
• Model-Based Reflex Agents: These agents maintain an internal model
of the world, allowing them to manage more complex situations by
considering the history of their interactions and predicting future
states.
• Goal-Based Agents: These agents act to achieve specific goals. They
make decisions by considering the desired outcome and the actions
needed to reach that goal.
• Utility-Based Agents: These agents aim to maximize a utility function,
which quantifies the desirability of different outcomes- decisions that
result in the highest overall benefit.
• Learning Agents: These agents can learn from their experiences and
improve their performance over time. They adapt their behavior based
on new data and feedback from their actions.

Real-World AI Agent Applications

• Personal Assistants: AI agents like Siri, Alexa, and Google Assistant
help users with tasks such as scheduling appointments, sending
messages, and providing information.
• Autonomous Robots: Robots like Roomba vacuum cleaners and
Amazon delivery robots operate autonomously to perform physical
tasks.
• Gaming Agents: AI agents in video games can play against human
players or other AI agents, providing a challenging and dynamic
gaming experience.
• Fraud Detection: Financial institutions use AI agents to detect
fraudulent transactions by analyzing patterns and identifying
suspicious activities.

98
 • Traffic Management: AI agents help manage traffic flow in smart cities
by monitoring traffic patterns and adjusting signals to reduce
congestion.

Why AI Agents Are Game-Changers

• Automation: AI agents can automate repetitive and time-consuming
tasks, freeing human workers to focus on more complex and strategic
activities.
• Efficiency: They can process enormous amounts of data quickly and
accurately, improving decision-making and operational efficiency.
• Scalability: AI agents can manage increasing workloads without a
proportional increase in resources, making them cost-effective
solutions for growing businesses.
• Adaptability: Learning agents can adapt to new situations and improve
their performance over time, making them suitable for dynamic
environments.

Advanced AI Agents in Action

The next generation of AI agents are also known as advanced AI Assistants or
advanced AI Copilots or Agentic AI.

Right now, most of us use AI to get information or ideas. For example, if we're
planning a trip and need recommendations on where to go, AI can provide us
with many options. However, we still make the final decisions, like choosing
the destination and booking the flight, hotel, and car.

99
But what if AI could manage all of that for you? Would you trust it to make
those decisions? This is the question researchers at DeepMind explored in a
recent report on how advanced AI assistants could change our lives.

An AI assistant, as defined in the paper, is a digital helper that can understand

and respond in natural language. Its main job is to plan and conduct tasks for
the user across different areas, meeting the user's needs and expectations.
These assistants act autonomously, make decisions, and perform actions
without constant user input. They can manage a variety of tasks by interpreting
instructions and using general capabilities like understanding and
processing language. They are different from simpler tools because they can
manage complex tasks and adapt to user preferences over time.

They made it clear: If AI agents become a reality, they could impact every part
of our lives, from our work to how we communicate, influencing our
identities and futures.

So, what opportunities do Advanced AI Assistants create?

• Boosting Research: They can speed up scientific discoveries by

summarizing research papers, suggesting new hypotheses, and
helping design experiments.
• Improving Cooperation: AI assistants can explore more cooperative
solutions in negotiations, enhancing human collaboration by finding
mutually beneficial agreements.
• Enhancing Communication: They can improve communication by
translating languages, rephrasing messages for clarity, and tailoring
communication to individual preferences.
• Democratizing Expertise: AI assistants can provide expert advice and
educational materials to anyone, making high-quality knowledge and
coaching accessible to all.

100
 • Combating Misinformation: They can help check facts and provide
context for disputed claims, promoting critical thinking and reducing
the spread of false information.
• Supporting Disabilities: AI assistants can offer real-time
communication assistance, personalize content, and help people with
disabilities make informed decisions about their health and wellness.
• Increasing Productivity: By automating routine tasks, AI assistants
can significantly boost productivity and job quality, allowing people to
focus on more meaningful work.
• Addressing Climate Change: They can aid in combating climate change
by raising awareness, developing environmental applications, and
improving productivity in related engineering efforts.

We're already moving in this direction. Microsoft's Copilot can solve complex
coding problems and will soon manage tasks like sending invoices and
rewriting app code. Alphabet is developing AI that can navigate the internet,
and new models like Devin can build custom websites from scratch.

However, this brings up tricky ethical issues. If AI starts acting on our behalf,
we need to decide who is responsible when it makes mistakes or violates societal
norms. An AI might make choices that benefit itself but harm others. It could
conflict or cooperate with other AI models it encounters. Additionally, it
would learn a lot about us, raising privacy concerns.

101
Imagine waking up to an empty inbox, an organized calendar, and a to-do list
that's done. That's the power of having something like an Athena Assistant
(from startup Athena).

They don't just hire top talent, they turn them (and you) into delegation
masters and train the top 0.05% to become an extension of you. The result?
600 hours per year saved. That's time back for you to achieve more. And the
cost? $3K a month…

102
Global AI Adoption: A Revolution in
Progress

The International Monetary Fund recently looked at which countries are best
prepared to integrate AI into their economies. The organization considered
multiple factors, including digital infrastructure — such as access to data
centers and advanced chips — and human capital — the pool of talent that AI
companies can tap into.

The AI Preparedness Index is a measure designed to evaluate how ready

different countries are to integrate and benefit from artificial intelligence
(AI) technologies. This index considers several key dimensions that
collectively determine a country's ability to adopt and leverage AI effectively.

The Ultimate AI Preparedness Index

The AI Preparedness Index assesses a country's readiness for AI adoption
based on the following dimensions:

• Digital Infrastructure: This dimension evaluates the availability and

quality of digital infrastructure, including internet connectivity, data
centers, and cloud computing capabilities. It reflects how well a
country is equipped with the necessary technological foundations to
support AI applications.

• Human Capital: This dimension measures the availability of skilled

labor capable of developing, implementing, and managing AI
technologies. It includes factors such as the education level of the
workforce, the presence of AI-related educational programs, and the
overall digital literacy of the population.

103
 • Labor Policies: This dimension assesses the policies in place to support
the workforce in adapting to AI-driven changes. It includes aspects
such as retraining programs, social safety nets, and labor market
regulations that facilitate worker transitions from displaced jobs to
new opportunities created by AI.

• Regulation and Innovation: This dimension examines the regulatory

environment and the extent of innovation within a country. It looks at
how well regulations support AI development and deployment, the
effectiveness of governance, and the level of investment in AI research
and development.

Inside the AI Preparedness Index

The index categorizes countries into three groups based on their level of
preparedness:

• Advanced Economies: These countries typically have robust digital

infrastructures, highly educated workforces, supportive labor policies,
and advanced regulatory frameworks. They are well-positioned to
exploit the benefits of AI and mitigate its potential downsides.

• Emerging Market Economies: These countries have varying levels of

preparedness. While they may have some digital infrastructure and a
growing pool of skilled labor, they often need to improve their
regulatory frameworks and labor policies to fully benefit from AI
technologies.

• Low-Income Developing Countries: These countries generally have

limited digital infrastructure and human capital. They face significant
challenges in adopting AI technologies and need substantial
investments in foundational infrastructure and education to build a
digitally skilled workforce.

104
Why AI Preparedness Matters
The AI Preparedness Index is crucial for policymakers, businesses, and
researchers as it provides a comprehensive assessment of a country's
readiness to embrace AI. It helps identify strengths and weaknesses in
different areas, guiding targeted interventions and investments to improve
AI readiness. By understanding their position on the index, countries can
better prepare for the economic and social transformations driven by AI,
ensuring that they can harness its benefits while minimizing potential
disruptions.

Summarizing, the AI Preparedness Index is a multidimensional tool that

evaluates a country's readiness for AI adoption by examining digital
infrastructure, human capital, labor policies, and regulatory environments.
It categorizes countries into advanced, emerging, and low-income
economies, providing valuable insights for strategic planning and policy
development.

Top Countries Leading in AI Adoption

According to the AI Preparedness Index, those countries that are best
prepared for AI adoption are primarily advanced economies with robust
digital infrastructures, highly educated workforces, supportive labor
policies, and advanced regulatory frameworks. These countries are well-
positioned to exploit the benefits of AI and mitigate its potential downsides.

Country AI Preparedness Index Score

Singapore 0.800566718

Denmark 0.778522253

105
United States 0.771269083

Netherlands 0.766493112

Estonia 0.764382198

Finland 0.758017361

Switzerland 0.757012427

New Zealand 0.753679782

Germany 0.753328815

Sweden 0.747799903

Advanced Economies vs. Emerging Markets

Advanced Economies: These countries have a higher concentration of jobs in

sectors requiring complex cognitive tasks, making them both more

106
susceptible to AI disruptions and better positioned to benefit from AI
innovations.

Emerging Market Economies: Countries like China and India are rapidly
improving their AI readiness, focusing on building digital infrastructure and
enhancing digital skills among their populations.

Challenges for Low-Income Developing Countries

Digital Divide: Low-income developing countries face significant challenges

in adopting AI due to limited digital infrastructure and human capital. These
countries need substantial investments in foundational infrastructure and
education to build a digitally skilled workforce.

Policy Recommendations

To harness AI's potential fully, countries should:

• Invest in AI Innovation: Advanced and more developed emerging

market economies should focus on AI innovation and integration.
• Develop Digital Skills: Emerging market and developing economies
should prioritize building a digitally skilled labor force.
• Enhance Regulatory Frameworks: All economies need to advance
adequate regulatory frameworks to optimize benefits from increased
AI use.
• Support Labor Reallocation: Implement social safety nets and
retraining programs for workers affected by AI-induced changes.

The countries best prepared for AI adoption are predominantly advanced

economies with strong digital infrastructures, educated workforces, and
supportive regulatory environments. Emerging markets are making strides,

107
but low-income developing countries require significant investments to
bridge the digital divide and build AI readiness.

The Rise of Generation AI

The United States can learn from ‘Generation AI’ in Asia Pacific in a recent
Deloitte article. Generation AI refers to children and young adults (up to 24
years old) who have grown up with smart devices, voice assistants,
recommendation algorithms, and other AI-powered technologies. They've
encountered AI in various parts of their lives, from entertainment and
education to healthcare and daily interactions since early childhood. Digital
fluency and ability to navigate and use AI technologies marks this generation.

• Students and employees are leading the generative AI revolution across

Asia Pacific, but only half believe their manager knows they're using it.
• Developing economies are at the forefront of generative AI adoption,
with uptake rates 30% higher than in developed economies.
• Generative AI impacts 1.1 billion work hours in Asia Pacific.
• Using generative AI saves each user a day per week, freeing up time to
learn new skills.
• Generative AI increases satisfaction levels at work and in studies.
• Three-quarters of businesses are falling behind on generative AI
adoption according to their own employees.

“Fifty-four percent of employees said they used the time savings to complete
other tasks while 45% invested time in additional learning or skill
development.”

108
 “Given that gen AI use increases employee satisfaction, businesses risk losing
employees to innovative competitors when they fail to engage their employees
on gen AI.”

So, what are the critical steps for US business leaders to take now?

1. Develop and implement a generative AI strategy that focuses on your

businesses’ core value areas.
2. Empower your employees to own their AI journey.
3. Develop your data infrastructure and data governance iteratively as
needed to embrace generative AI.

As Generation AI continues to reshape the Asia-Pacific region, it's crucial for

employers to adapt to and embrace rapid AI advancements. By doing so,
organizations can keep up with the evolving workforce and capitalize on the
immense potential generative AI offers for economic and societal
transformation. The future of work in the region depends on harnessing
generative AI's power to foster collaboration and innovation among
employees and employers alike.

109
Postface
As we conclude "AI Unleashed: Revolutionizing Our World with Cutting-
Edge Technology," it's clear that we stand on the brink of a new era. The
insights and predictions shared by our featured visionaries highlight the
immense potential of AI to transform every aspect of our lives. This
technology is not just a tool but a partner that can amplify human capabilities
and drive unprecedented progress.

Reflecting on the lessons from this book, it's evident that the future of AI is
both promising and challenging. We must approach it with a blend of
optimism and caution, ensuring that we harness its power responsibly. The
ethical and governance issues discussed in these pages remind us that with
great power comes great responsibility. As AI continues to evolve, it is crucial
to establish robust frameworks that guide its development and application,
ensuring it serves the greater good.

For individuals and businesses alike, the key takeaway is the importance of
adaptability and continuous learning. AI will undoubtedly reshape the job
market, creating new opportunities while rendering some roles obsolete.
Embracing this change means staying informed, acquiring new skills, and
being open to new ways of working. By viewing AI as a collaborator rather
than a competitor, we can unlock its full potential and create a symbiotic
relationship that benefits everyone.

Looking ahead, the integration of AI into our daily lives will become even
more seamless. From personalized healthcare and autonomous
transportation to smart home systems and AI-driven creativity, the
possibilities are endless. This book has shown that you do not have to fear the
future but embrace it with excitement and preparation.

Thank you for joining us on this exploration of AI's transformative power. As

you move forward, remember that the knowledge you've gained here is just

110
the beginning. Stay curious, stay informed, and continue to explore the ever-
evolving landscape of artificial intelligence. Together, we can shape a future
where AI enhances human potential and drives positive change across the
globe.

111
The Generative AI CA$H Machine
Book Series

Generative AI CA$H MACHINE – Volume 1

AI Profit Hacks
Turn Your Skills into Cash with Generative AI

112
 Generative AI CA$H MACHINE – Volume 2

Digital Domination
Boost Your Sales with AI-Enhanced Digital Products

Generative AI CA$H MACHINE – Volume 3

AI Profit Playbook
Unleash Proven Tactics for Massive AI-Driven Earnings

113
 Generative AI CA$H MACHINE – Volume 4

Traffic Explosion
Unleash Hidden Traffic Goldmines

Generative AI CA$H MACHINE – Volume 5

AI Unleashed
Revolutionizing Our World with Cutting-Edge Technology

114
 Stay Informed
Stay informed on your journey through the dynamic landscape of artificial
intelligence, where ChatGPT and its companions serve as our guides. We will
send you our FREE Volume 1 (AI PROFIT Hacks) from our Generative AI CA$H
Machine book series. Additionally, jumpstart with your UNFAIR
ADVANTAGE, our FREE AI Text Prompts guide.

115
➜ Glossary
Artificial Intelligence (AI): A super-smart computer system that can mimic
human activities like understanding speech, making decisions, and learning
from experience.

Copilots: AI assistants that help with tasks like writing and coding, making
you more productive.

Frontier Models: Innovative AI systems with advanced capabilities.

Generative AI: AI that creates new content like pictures, music, or text by
learning patterns from existing data.

GPU (Graphics Processing Unit): Powerful computer chips essential for AI

tasks, originally designed for video games.

Grounding: Making AI more accurate by connecting it to real-world data.

Hallucinations: When AI generates incorrect or unrealistic information

because it cannot distinguish between real and fake data.

Large Language Models (LLMs): Advanced computer systems that learn to

understand and use human language by analyzing enormous amounts of text.

Machine Learning: A way to teach computers by showing them patterns in

data so they can make predictions and improve over time.

Memory: Temporary or long-term storage of information by AI to provide

better answers.

Multimodal Models: AI systems that can process several types of data (e.g.,
text, images, sounds) at the same time.

Orchestration: Managing AI tasks in the right order for better responses.

Plugins: Add-ons that extend an AI system’s capabilities, like apps on a

smartphone.

116
Prompts: Instructions given to an AI to tell it what task to perform, like giving
an order at a deli.

RAG (Retrieval Augmented Generation): Using external data sources to

improve AI's accuracy without retraining it.

Reasoning/Planning: AI solving problems and making plans, like organizing

a detailed schedule for a trip.

Responsible AI: Ensuring AI systems are safe, fair, and unbiased by carefully
designing and monitoring them.

SLM (Small Language Model): A smaller, more efficient version of a large

language model, suitable for devices like phones.

Training/Inference: Teaching AI with data (training) and using it to make

predictions (inference).

Transformer/Diffusion Models: Advanced models for language

understanding (transformers) and image creation (diffusion).

117
BONUSES

118
 BONUS
➜ Indispensable AI Tools
ChatGPT can only get you so far. Take the AI generated text and convert it to
video or to digital products or to physical products with these AI tools that
will change how you work or run your income generating business.

There are also tools to help you start and run your business (identifying
niches, products on Etsy, keywords, and more).

Digital Content Design

Canva

Canva is a versatile graphic design platform that empowers individuals and

teams to create stunning visuals with ease. Whether you are a seasoned
designer or a complete beginner, Canva provides a user-friendly interface
and a wealth of resources to unlock your creative potential. Here are 5 of
Canva's top features:

• Ready-to-use templates: Choose from thousands of professionally

designed templates for presentations, social media posts,
infographics, resumes, and more. Customize them to fit your specific
needs.
• Drag-and-drop interface: Easily create visual content without any
prior design experience. Simply drag and drop elements onto your
canvas, resize and rearrange them to create a unique and impactful
message.

119
 • Extensive library of multimedia elements: Access millions of photos,
illustrations, icons, fonts, and other design elements to enhance your
visual creations.
• Brand management tools: Maintain brand consistency with custom
color palettes, fonts, logos, and team-specific templates.
• Collaboration tools: Work seamlessly with your team on designs in
real-time, leaving comments and feedback for effortless
communication and project completion.

Sign up for a free Canva account here.

Analysis Tools for Etsy Stores

EverBee

EverBee is a product analytics tool for Etsy sellers that helps you find trending
products, see how competitors are performing, and make informed product
decisions to grow your business. Here are the top 5 features of EverBee:

• Product Research: Find high-demand products to sell on Etsy.

• Revenue Analytics: See how other Etsy listings are selling so you can
make high-revenue products.
• Save Time: Only make & sell what people are proving to buy.
• Create Best-Sellers: So, you can create a growing & sustainable
business.
• 1-Click Data Insights: Estimated monthly sales, revenue, favorites,
tags, reviews, and more in just a click.

Sign up for a free EverBee account here.

eRank
120
eRank is a comprehensive search engine optimization (SEO) tool designed
specifically for Etsy sellers. It helps you optimize your listings for search,
track your competitors, and discover trending products to grow your
business. Here are five of eRank's top features:

• Keyword Research: Uncover high-volume keywords that real Etsy

shoppers are using to find products like yours.
• Listing Audit: Identify areas where you can improve your listings to
make them more search-friendly and boost your rankings.
• Listing Details: Get a detailed overview of your active listings, including
thumbnail images, stats, and optimization suggestions.
• Competitor Tracking: Keep an eye on your Etsy competitors by tracking
their daily sales, listings, and the keywords they use.
• Trends: Stay on top of the latest trending items on Etsy and other
platforms so you can create profitable products that are in demand.

Sign up for a free eRank account here.

Marmalead

Marmalead is a comprehensive Etsy SEO tool that helps sellers identify high-
volume keywords, optimize their listings, and track their competitors to
improve their visibility in Etsy search and boost their sales. Here are five of
Marmalead's top features:

• Keyword Research: Discover high-value keywords that real Etsy

shoppers are using to find products like yours.
• Listing Optimization: Get actionable recommendations to optimize
your listings for search, including title, description, tags, and category
placement.

121
 • Search Volume Analysis: Understand the search volume for relevant
keywords to determine their effectiveness in attracting potential
customers.
• Competitor Analysis: Track your Etsy competitors' keyword usage,
listing performance, and overall shop traffic to gain valuable insights.
• Performance Tracking: Monitor your shop's search rankings, traffic,
and conversion rates to assess the impact of your SEO efforts.

Sign up for a free Marmalead account here.

122
Text to Image

Midjourney

Midjourney is a text-to-image AI model that can generate images from text

descriptions. It is known for its ability to create detailed and realistic images
and used by artists and designers to create a variety of creative content.

Sign up for a free Midjourney account here.

Stable Diffusion

Stable Diffusion is another text-to-image AI model that is like Midjourney. It

is known for its stability and speed, and it can generate high-quality images
with less training data than other models.

Sign up for a free Stable Diffusion account here.

Adobe Firefly

Adobe Firefly is an AI-powered image editing tool helping users create and
edit images with ease. It offers a variety of features, including automatic
image enhancement, object removal, and background replacement.

Sign up for a free Adobe Firefly account here.

Leonardo AI

Leonardo AI is a text-to-art AI model that can generate images, 3D models,

and code from text descriptions. It is known for its ability to create creative
and original content and used by artists and designers to create a variety of
unique and innovative creations.

Sign up for a free [Link] account here.

Microsoft Image Creator

123
Microsoft Image Creator is a text-to-image AI model helping users create
images for presentations, social media, and other purposes. It offers a variety
of features, including automatic image generation from text descriptions,
image editing tools, and a library of templates.

Sign up for a free Image Creator account here.

Text to Music

Mubert

Mubert is a platform powered by music producers that helps creators and

brands generate unlimited royalty-free music with the help of AI. Mubert's
mission is to empower and protect the creators.

With Mubert Render, you can enter anything — an abstract phrase, the name
of a genre or mood, or a description of what is happening in your content.
Mubert will generate a suitable track with a duration of up to 25 minutes.

Sign up for a free Mubert account here.

Text/Video Scripts to Video

Pictory AI

Pictory is a video creation platform that utilizes artificial intelligence (AI) to

empower businesses and individuals to create engaging and shareable videos
in a matter of minutes. It offers a variety of features that simplify the video
production process and enable users to produce high-quality content without
extensive editing experience. Here are five of Pictory's top features:

124
 • AI-powered video generation: Transform any text, script, or blog post
into a captivating video using Pictory's AI technology.
• Customizable video templates: Choose from a vast library of
professionally designed video templates tailored to various industries
and purposes.
• Vast media library: Access a vast collection of royalty-free images,
videos, music, and sound effects to enhance your video creations.
• Real-time collaboration: Collaborate seamlessly with team members
on video projects in real-time, providing feedback and suggestions for
efficient workflow.
• Multiple video formats: Export your videos in various formats,
including social media-friendly sizes, to cater to different platforms
and audiences.

Sign up for a free Pictory account here.

Use the discount code ‘BorneoAG’ for 20% OFF throughout the entire
duration of your subscription.

Print-on-Demand

Printify

Printify offers a wide range of customizable items, including apparel like T-

shirts, hoodies, and leggings, as well as accessories such as phone cases,
mugs, and posters. They connect businesses with a network of global printing
partners, allowing for diverse product options and competitive pricing.

Sign up for a free Printify account here.

Printful

125
Printful provides a similar service with a focus on high-quality print and a
user-friendly interface. They offer a variety of products like T-shirts, hats,
tote bags, and more. Printful also integrates with various e-commerce
platforms, streamlining the order fulfillment process for online stores.

Sign up for a free Printful account here.

HelloCustom

Personalizing custom POD products has never been easier! With the simple
click of a button, automatically personalize your Etsy product graphics. The
rest of your POD business is automated, so why can’t your personalized POD
products be too? Personalize and fulfill orders with the simple click of a
button.

Sign up for a free HelloCustom account here.

126
 BONUS
➜ Learn How to Generate a
Passive $30K/month

Need someone who has done it all on Etsy to mentor and help you build your
Etsy business? Meet Etsy Star Seller Anne Maud of Upstrider. Anne specializes
in instructing others on the transformation from zero to achieving a
consistent daily sales count of 30 or more, exclusively within the realm of
online commerce. Her teaching revolves around harnessing pre-existing
passions, skills, or past experiences to monetize oneself, with platforms like
Etsy, websites, or sales pages serving as the means.

Operating under the name Upstrider, Anne's mission centers on assisting

individuals in surmounting self-limiting beliefs to construct a robust online
presence and effectively convert their life experiences, skills, traumas, and
passions into a source of income. Her aspiration is to serve as a supportive
mentor, akin to a dependable older sibling, offering guidance and knowledge
to ambitious individuals who possess significant dreams and untapped
potential, and are resolute in their pursuit of personal excellence. Despite
facing numerous challenges and enduring a steep learning curve marked by
trials, errors, and countless late nights, Anne managed to establish two
brands from scratch in under two years, propelling both to the impressive
milestone of one million in sales.

127
Discover the new Upstrider Bespoke 30k+ Business Plan and learn how to
transform what you already know, love, or have already built into a thriving
online business, starting with Etsy and sales funnels. Work from home,
generate passive income and achieve £30,000 or US$30K in monthly sales
with actionable step-by-step tasks designed just for you.

With the 90-day plan, she will work with each individual business owner to
create a tailored strategy that leverages your skills, experiences, and even
your personal challenges to monetize your passions through digital products,
for passive income. Whether you are just starting out or looking to scale your
existing small business, she is there to help you achieve your goals and create
an impactful brand that resonates with your audience.

She will craft personalized content and strategies for you, from your email
marketing sequences, lead magnets, to your brand story, mission, values,
your content strategy on social media and much more - implement a strong
strategy together and take that business OFF THE GROUND, fast.

All this for a 100% Money-Back Guarantee!

Find Out How Here

128
129