Discover how AI works and explore foundational AI concepts, such as machine learning (ML). Learn about the rise of generative AI and how to perform tasks with it. By the end of this module, you’ll have an understanding of the capabilities and limitations of AI tools and how to integrate generative AI in the workplace.
Learning Objectives
- Define the field of AI.
- Explain how AI functions at a basic level, including how AI technology is trained to learn from data.
- Describe the capabilities and limitations of AI tools.
- Recognize the importance of human oversight when using AI.
Welcome to the exciting world of AI
Video: Introduction to Google AI Essentials
Key Points
- AI’s Transformative Power: AI has the potential to revolutionize how we work, streamlining routine tasks and freeing up time for higher-level work.
- Boost Your Career with AI: Understanding and using AI tools effectively can make you more productive, valuable, and future-ready.
- Google AI Essentials Course: This self-paced, beginner-friendly course from Google experts will help you:
- Understand what AI is and how it works.
- Use AI tools for practical work benefits.
- Learn about responsible and ethical AI use.
- Earn a skill badge to showcase your AI knowledge.
Call to Action: The course encourages you to explore how AI can enhance your work and prepare you for the evolving workplace.
- Join me as we uncover the ways AI can enhance your career and life. There’s a big shift happening
in the modern workplace, and AI is at the forefront of
this exciting transformation. Just as the internet
forever changed the way we approach everyday
tasks, AI has the potential to transform the way we work and live. AI stands for artificial intelligence. It’s a practical solution for making routine tasks
less time-consuming. Learning to use AI effectively in your job can help you to accomplish
your goals and set you up for success in the
evolving work landscape. For example, consider a
typical day at your work. If it’s anything like mine, you have a lot of tasks to complete. Some days your to-do list
might seem never ending, but what if AI could help? For instance, instead of spending hours reviewing spreadsheets,
AI can help you analyze the information in seconds. It can also draft a detailed sales report, highlighting key insights
to share with your team. AI can schedule meetings for you, creating engaging presentations, enhance your brainstorming sessions and take on a variety of other tasks that will shorten your to-do list. Whether you’re curious to
learn the basics of AI, interested in making routine tasks easier, or focused on enhancing your skillset we’ve designed Google
AI Essentials to help. Hi, my name is Maya and I’m
the Vice President of Strategy and Operations at Google Research. In my role, I lead a team
that helps Google achieve its mission by accelerating research and fostering an exceptional
research environment. I’m thrilled to be your guide
on this journey to explore this technology that’s reshaping
the business world, AI. Throughout the course,
you’ll have the opportunity to learn from a diverse
group of AI experts at Google whose role span from program management to directors of AI products and services. They’ll each share their insights into AI, and how it can elevate your
work and advance your career. Google AI Essentials is
designed to fit your schedule. You can complete it at
your own pace all online and no previous AI
experience is necessary. This course will include
videos from Google employees who work in AI, readings to help deepen your understanding of concepts
and interactive activities that give you practical
experience working with AI. At the end of the course,
you’ll have the opportunity to earn a skill badge that can
be displayed on your resume, social media profiles,
and email signature. If you’re new to AI, you may
have many unanswered questions. You might wonder, “How
do I engage with AI tools to boost my productivity?” “How do I apply AI responsibly in my job?” Or, “How should I prepare for the future of AI in the workplace?” In Google AI Essentials, we’ll address each of those questions and more. I hope you’re excited to join me as we uncover the ways AI can enhance your career and life, let’s get started.
Video: AI and the future of work
Key Points
- AI is Becoming Essential: AI is rapidly becoming a standard tool for modern businesses.
- Understanding AI is Key: Just like knowing driving rules makes you a better driver, understanding AI helps you use it effectively and avoid pitfalls.
- What is AI? In this context, AI refers to computer programs that mimic human cognitive tasks, aiding with decision-making and problem-solving.
- AI’s Potential: AI can improve work quality and efficiency, but it’s not a magical fix-all. Responsible use requires understanding its strengths and limitations.
Call to Action: The Google AI Essentials course promises to dive deeper into how AI works and how it can benefit your work.
- In today’s fast-paced world, AI is quickly becoming a standard tool in every company’s toolkit. Navigating the emergence
of AI in the workplace is similar to driving down a busy street. Just as knowing the rules of
the road can make you a better and more effective driver, understanding the basics
of AI can help you to reach your destination safely and to avoid potential roadblocks. To begin this AI journey,
let’s start by examining what the term artificial
intelligence really means. In this context, intelligence
refers to the human ability to perform cognitive tasks. A cognitive task is any mental
activity such as thinking, understanding, learning, and remembering. As humans, we have cognitive
abilities that allow us to make decisions and solve problems. However, there are also
limits to how much information we can process at a time. AI is capable of extending
our cognitive abilities, helping us to make better decisions and solve problems faster. With that understanding, the
term artificial intelligence refers to computer programs that can complete cognitive tasks typically associated
with human intelligence. Simply put, AI programs
can assist us with tasks by using math to learn from data. As you’ll soon discover,
AI has the potential to greatly improve the
quality of our work lives and streamline business operations. However, AI isn’t a magic solution to every business problem. As with any advanced tool, the key is to use AI to its strengths, and doing so requires careful thought and consideration of the
technology’s capabilities. Are you curious to discover how AI works? Wanna find out how AI
can enhance your work? Then get ready to explore
these questions with me in Google AI Essentials.
Video: Learn from AI success stories
AI’s Transformative Power Across Industries
- HR and Management: Companies like UKG are using AI to enhance decision-making in the following ways:
- Easier and faster access to insights for employees
- Advanced analytics for managers to inform business choices
- Agriculture: Companies like Jiva are using AI to help farmers address challenges and improve their practices:
- AI-powered crop disease diagnosis and treatment suggestions.
- Insights for better quality crops and increased yields.
- Across every industry, AI is introducing new approaches to work. Companies and organizations of every type are developing innovative solutions to a variety of workplace
tasks and challenges, all with the help of AI. Let’s explore some examples of how AI is reshaping the way people
work all across the globe. Consider UKG, a provider of HR and workforce management solutions. By integrating AI into its product suite, UKG is improving how its employees analyze information and insights. This can make it easier and faster for employees to receive answers to their work-related questions. EKG’s AI integration also enables managers to gain advanced analytics
from user interactions, helping them make more
informed business decisions. Now let’s consider one
of the oldest industries in the world, farming. AI is also being used to address many challenges
in this industry. For example, a common challenge that rural farmers face each
year is economic uncertainty due to a variety of factors. One is frequent changes with
crop and livestock yields. Other factors include
unpredictable weather conditions and limited access to
advanced farming techniques. Uncertainties like these
can make it difficult for farmers to make
effective business decisions. Jiva is an agricultural company focused on helping rural farmers solve these types of challenges. As part of their mission, Jiva provides farming
communities with AI solutions that can assist them in
achieving sustainable and reliable farming practices. Jiva uses AI tools that can diagnose crop
diseases and suggest remedies. Farmers can also receive
relevant AI-powered advice that helps them produce
better quality crops and increased yields. With the help of AI,
Jiva helps rural farmers stay informed and access more insights that can improve their business. Overall, AI can be a powerful tool for all kinds of business activities. And no matter the industry,
AI has a potential to transform how companies
and organizations develop innovative,
forward-thinking solutions. As you continue your journey
into the world of AI, consider this, in what ways can AI positively impact your industry, and how can you be part of that change?
Video: Maya: The exciting world of AI
Key Points by Maya (VP, Google Research)
- Google Research Focus: Identifies societal problems and seeks innovative solutions, often leveraging AI.
- Example: Contrails Project: Using AI to research ways to reduce the negative climate impact of aviation.
- AI’s Widespread Integration: Most modern technologies have an AI component or are closely related to the field.
- AI’s Positive Potential: Maya is hopeful about AI’s ability to improve lives and society. We’re only at the beginning of what’s possible.
- Personal Purpose: Maya sees AI as a powerful tool for alleviating suffering and advancing humanity.
- Invitation: Emphasizes that AI is approachable and welcomes everyone to participate in its development and use.
- I am Maya. I’m Vice President of
Strategy and Operations at Google Research. Day to day, Google Research
is trying to figure out, what are the things
that can change society and our business today,
tomorrow, and in the future? We start by saying, you know, what’s impossible in people’s minds? What are problems that need to be solved? And how can we apply the
expertise that we have to those problems to provide a solution that benefits all of us as
people and also our business? One piece of technology at Google Research we’re very proud of at this moment, because there’s so many
that we’ve had in the past that utilize AI, is around Contrails, which is, when you look up at the sky and you see the white
trail from behind a jet, and utilizing AI to try to understand how can we alleviate that, because it has a very
negative impact on climate. Most technologies nowadays
have either an AI component or an adjacency to AI. I’m very hopeful that AI tools
will have a tremendous impact in a positive way on us as people. I think that we’re just at
the beginning of that journey. AI is one tool that I consider a powerful one in achieving my life’s purpose, which is to alleviate suffering and to help us progress as
people to a better place, to have a better society,
to have a better world. It’s not something that’s not approachable and something that people
need to be intimidated by. We are all welcome on this journey.
Discover how AI works
Video: Explore how AI uses machine learning
AI: More Than a Trend
- AI might seem like a recent buzzword, but it’s been used for years in familiar features like streaming recommendations.
- AI tools, powered by machine learning (ML), are used in various industries to improve operations and products.
- ML is a subset of AI where programs learn to make decisions by analyzing data.
How AI Tools Work
- ML models require training sets (large collections of data) to learn how to identify patterns and respond.
- An example is a food distributor using AI to sort ripe apples. The ML model is trained on many images of ripe and unripe apples to perform the task.
- It’s important to be aware of potential bias in training data, which can lead to inaccurate results from the AI tool.
Conclusion
- ML is crucial for advancing AI. It has significant potential, but it’s important to use it consciously and address potential biases within training data.
Llama3
The article discusses the concept of Artificial Intelligence (AI) and its relationship with Machine Learning (ML).
While AI has been around for some time, it has gained significant attention recently due to its numerous
applications in various industries. The article highlights how streaming platforms use AI-powered software to
recommend videos that users might enjoy. Additionally, companies employ AI tools to streamline operations and improve product quality.
The article explains that ML is a subset of AI focused on developing computer programs that can analyze data to make decisions or predictions. ML uses a training set, which is a collection of data used to teach the AI program, to learn and identify patterns. The example given is an AI tool used by a food distributor to sort ripe apples, where the AI designer trains an ML program using images of ripe and unripe apples.
The article emphasizes that the quality and relevance of training data are crucial for ML programs to perform
effectively. However, it also notes that there is a potential issue with bias within training data, which can
cause AI tools to produce inaccurate or unintended outputs. The example given is an AI tool used to sort apples, which may learn from biased training data and incorrectly sort apples.
Overall, the article highlights the importance of ML in advancing AI technology and its numerous applications
across various industries.
- All the buzz surrounding
AI can make it seem like the hottest new tech trend, but the truth is AI has
been around for a while. For example, have you ever wondered how streaming platforms
recommend videos you might like? This feature is brought to you by AI. For years, streaming
platforms have used AI tools to offer services, like
recommendation systems that enhance the user experience. An AI tool refers to AI powered software that can automate or assist
users with a variety of tasks. Examples of AI tools are everywhere, from GPS systems that suggest quick routes to translation systems that
interpret conversations in real time. Companies of all shapes
and sizes use AI tools to streamline operations
and improve the quality of their products and services. While these AI tools can
seem naturally smart, it’s important to recognize
that they’re not self-taught. Instead, they’re powered by what’s known as machine learning. Machine learning, or ML, is a subset of AI focused on developing computer programs that can analyze data to make
decisions or predictions. ML is a specialized layer
under the broader category of AI technology. It’s often used by AI tools to make sense of data quickly and efficiently. AI designers build ML
programs using a training set, which is a collection of
data used to teach AI. Basically, training
sets provide ML programs with examples of what to expect and how to respond appropriately. For example, consider a food distributor that uses an AI tool to
sort and pack ripe apples in their factory. For this tool to work, an
AI designer must first train an ML program to identify ripe apples. They would do this by
providing their ML program with a training set that
includes thousands of images of ripe and unripe apples. As the ML program processes these images, it eventually learns to
identify the features of ripe apples. Having learned to do this with ML, the AI tool can then identify ripe apples that weren’t in its training set, and help factory employees
work more efficiently. As I mentioned earlier,
many AI tools use ML to learn and improve their performance. However, for ML programs
to perform effectively, the quality and relevance of
their training data matter. A fundamental issue to be aware of is the potential for bias
within training data. This could unintentionally
cause an AI tool to produce inaccurate
or unintended outputs. For example, the AI tool that was used to sort ripe apples might’ve
learned from training data that only contain images of
specific types of red apples. This would unintentionally
make the AI less accurate at identifying ripe
apples of varying sizes, shapes, or colors. The food producer might end
up sorting apples incorrectly, causing them to lose money and
waste perfectly good apples. When used appropriately,
ML plays a key role in advancing AI into the future. It’s truly an incredible
and sophisticated technique with endless applications.
Video: Foundations of generative AI
- Generative AI is changing how we work. This type of artificial intelligence can create new content (text, images, audio, etc.) and understands natural language, the way we normally communicate.
- How it Works: You provide input (text, speech, sometimes images/video), the AI tool processes this input, and then generates an output based on your instructions.
- A Powerful Tool: Generative AI can save you time and effort. Examples include:
- Creating marketing materials when you don’t have a design team.
- Drafting email replies quickly.
- Brainstorming ideas and getting help with decision-making.
- Wide Applications: Generative AI tools exist to benefit a huge range of fields, including healthcare, education, and business.
- Conversational AI Tools: These are a specific type of generative AI focused on text-based conversations to answer questions, brainstorm, and boost productivity.
- Google’s Gemini: This conversational AI can offer creative ideas, build upon your concepts, and provide explanations to help you learn.
- AI’s Limits: While generative AI offers many possibilities, it’s important to understand the limitations of AI as a whole before diving fully into the technology.
- Advancements in AI technology
are reshaping how we work. Let’s explore one of the key developments at the center of this
transformation, generative AI. As the name suggests, generative AI is AI that can generate new content such as text, images, or other media. A unique quality of generative AI tools is that you can use them
with natural language. Natural language refers
to the way people talk or write when communicating
with each other. Here’s a simplified overview of how a generative AI tool
works with natural language. First, you provide input. Input refers to any information or data that’s sent to a
computer for processing. Many generative AI tools,
accept text and speeches input, and some also accept
images or video files. Next, the data is
processed by the AI tool. Then an output is generated
in the form of text, images, audio, or video. Generative AI and the ability to interact with computers using natural
language has introduced a world of possibilities for what
people can create with AI. For example, you might be
marketing a new business. You need fresh, engaging content
like a promotional poster to advertise a new product, but you don’t have a creative team to bring your ideas to life. No need to stress. With a few instructions, generative AI can help
you create a poster. If the generated content
doesn’t meet your expectations, you can provide additional instructions until it produces something
that meets your needs. This is just one example of how generative AI can
complement your skills, but there are many other ways it can benefit you and your work. For example, generative AI
can boost your productivity by helping you with tasks like
drafting replies to emails. It can help you avoid mistakes, and it can improve your
decision-making process by answering questions and
brainstorming ideas with you. Whether you work in healthcare,
education, finance, retail, or any other field,
there are a wide variety of generative AI tools that
can cater to your needs. One example is a conversational AI tool. A conversational AI tool
is a generative AI tool that processes text requests
and generates text responses. You can use it to brainstorm
ideas, answer questions, and boost your productivity. Throughout Google AI Essentials, you’ll gain practical experience using a conversational AI
tool by Google called Gemini. Gemini can be used to get some creative inspiration
when you’re feeling stuck, build on your ideas, and provide detailed explanations that help you explore topics easily. For example, let’s ask
Gemini to brainstorm a list of team-bonding activities
for our summer work retreat. The AI tool responds with
a wide range of ideas from a fun beach party to
a relaxed pottery class. Gemini also share some additional tips to consider when planning
a successful work retreat. Generative AI has paved the
way to exciting new frontiers, but before we can tap
into what this technology has to offer, it’s essential
to investigate the capabilities and limitations of AI as a whole. Continue to the next part of
this lesson to get started.
Reading: A guide to AI and ML
Reading
Artificial intelligence (AI) and machine learning (ML) are changing the future of work. Knowing the basics of both can help you navigate this evolving landscape. You’ll be able to contribute to AI-driven projects, find new ways for your organization to use AI and ML, and lead your own initiatives.
In this reading, you’ll explore some of the techniques AI designers use to build AI programs. You’ll deepen your understanding of ML programs and how data is used to train them. You’ll also explore how ML has paved the way for generative AI.
AI development techniques
Artificial intelligence refers to computer programs that can complete cognitive tasks typically associated with human intelligence. There are two main techniques used to design AI programs:
- Rule-based techniques involve creating AI programs that strictly follow predefined rules to make decisions. For example, a spam filter using rule-based techniques might block emails that contain specific keywords using its predefined logic.
- Machine learning techniques involve creating AI programs that can analyze and learn from patterns in data to make independent decisions. For example, a spam filter using these techniques might flag potential spam for the recipient to review, preventing automatic blocking. If the recipient marks emails from trusted sources as safe, the spam filter learns and adapts its logic to include similar emails from that sender in the future.
AI tools can use either rule-based or ML techniques, or even a combination of both. In general, rule-based techniques are commonly used for tasks that require rigidity, such as blocking messages from untrusted senders that are obviously spam, like requests for bank transfers or private information. Conversely, ML techniques are better suited for tasks demanding flexibility and adaptability, like learning to recognize that messages from trusted senders containing typos are not spam.
Approaches to training ML programs
Recall that machine learning is a subset of AI. It develops computer programs that can analyze data to make decisions or predictions. AI designers often use ML in their AI programs because it doesn’t have the limitations of rule-based techniques.
There are three common approaches to training ML programs:
- Supervised learning
- Unsupervised learning
- Reinforcement learning
Supervised learning
In this approach, the ML program learns from a labeled training set. A labeled training set includes data that is labeled or tagged, which provides context and meaning to the data. For instance, an email spam filter that’s trained with supervised learning would use a training set of emails that are labeled as “spam” or “not spam.” Supervised learning is often used when there’s a specific output in mind.
Unsupervised learning
In this approach, the ML program learns from an unlabeled training set. An unlabeled training set includes data that does not have labels or tags. For instance, it might be used to analyze a dataset of unsorted email messages and find patterns in topics, keywords, or contacts.. Unsupervised learning is often used to identify patterns in data without a specific output in mind.
Reinforcement learning
In this approach, the ML program learns from feedback for its decisions. Reinforcement learning is a trial-and-error approach that’s typically used for tasks that require a series of decisions, like a conversational AI tool. When a conversational AI tool gives an appropriate response to a question, it receives positive feedback from its AI designers and learns to answer similar questions in that way.
Each ML technique has its own strengths and weaknesses. AI designers may use one, two, or all three of these techniques as they develop solutions. It all depends on the type of data that’s available and what’s needed to solve the problem.
Generative AI
Advancements in machine learning have helped pave the way for generative AI—AI that can generate new content, like text, images, or other media. This type of AI often uses a combination of supervised, unsupervised, and reinforcement learning to create original content.
For instance, all three approaches play distinct roles in conversational AI tools. Supervised learning equips conversational AI tools with foundational dialogue data, enabling them to respond to common conversational cues appropriately. Unsupervised learning enables them to interpret nuances in language, like colloquialisms, that occur naturally in conversation. Reinforcement learning further strengthens these tools by allowing them to improve their responses in real-time based on user feedback. This enables them to adapt to the conversational context and engage in natural conversations.
Generative AI’s ability to create and innovate offers a range of benefits to all sorts of workplaces and professions, such as marketing, product development, engineering, education, manufacturing, and research and development. These benefits include:
- Greater efficiency: Generative AI can automate or augment routine tasks, allowing workers to focus on other work priorities.
- Personalized experiences: Generative AI can tailor its interactions to individual preferences and needs.
- Better decisions: Generative AI can quickly analyze vast amounts of data to uncover useful insights.
These are just some of the ways that generative AI can enhance your work.
For more information
PAIR Explorables is an optional resource for anyone who wants to learn more about AI. It is a collection of interactive articles that are designed to make key AI concepts more accessible and understandable. PAIR Explorables covers a wide range of topics, including:
- Machine learning basics
- Fairness and bias in AI programs
- Data and privacy considerations in AI
- Potential risks and benefits of AI
Each article features visualizations and interactive controls that can help you explore different AI concepts and experience how they work.
Mark as completedLikeDislikeReport an issue
Video: Understand the capabilities and limitations of AI
AI as a Powerful Tool (with Limitations)
- You don’t need to be a tech expert to use AI to improve your work.
- AI tools offer benefits:
- Content generation (like marketing videos).
- Quick analysis of information (summarizing emails).
- Detailed answers to questions.
- Simplifying your day-to-day tasks.
- However, AI has limitations that require human oversight:
- AI doesn’t learn independently, needing constant updates.
- Training data can contain biases, leading to unfair results.
- AI can produce inaccurate outputs called “hallucinations”.
Example of AI’s Limitations: A sales manager using AI to analyze data might be misled by inaccurate results that don’t consider all factors, leading to poor decisions.
Key Takeaways
- Human oversight of AI outputs is essential to ensure accuracy and ethical use.
- Successful AI in the workplace needs collaboration across different roles.
- An inclusive approach, with humans in control, is the best way to make AI work for everyone.
- Just as you don’t need to be
a carpenter to use a hammer, you don’t need to be a computer expert to use AI effectively. That said, understanding
the basics of what AI can do will help you make the
most of the technology. Today’s AI tools can do a
lot to enhance your work. They can generate content, like assisting a marketing team by making a promotional
video for a new product. They can analyze information quickly, like highlighting the key
points of a long email thread. They can answer questions in
a detailed and nuanced way. And overall, they can
simplify your day-to-day and allow you to focus on
other aspects of your work. While AI can complete a variety of tasks, there are some tasks that
require a human touch, such as handling sensitive issues. These limitations can be
critical in certain contexts. For example, AI can’t learn independently. It needs people to continually
update its training. Shortcomings in an AI tool’s training data can also potentially
reflect or amplify biases, leading to skewed or unfair outcomes. Another major limitation is that AI output can
sometimes contain inaccuracies, otherwise known as hallucinations. Hallucinations are AI
outputs that are not true. These inaccuracies can
range from minor errors, such as a sentence that
doesn’t make sense, to significant distortions. For instance, consider a sales manager who’s using an AI tool to
analyze quarterly sales data. The AI tool might identify declining sales of a particular product, and flag the item as something that should
be removed from stores. However, what if there
were a seasonal factor affecting sales that hadn’t been accounted
for in the AI tool’s analysis? Hallucinations like this one
can lead to misguided decisions if the user doesn’t carefully
review the AI tool’s output. Considering AI’s limitations, human oversight over AI
generated output is crucial to ensure that the information
is accurate and ethical. Effective management
of AI in the workplace requires teamwork from
technical to non-technical roles to ensure that AI’s output
and decision making processes are aligned with values
that benefit people. Ultimately, an inclusive approach that maintains human
oversight over these tools is the key to shaping a brighter future where AI works for everyone.
Video: Vint: Use AI for positive change
Vint Cerf: Internet Pioneer and AI Advocate
- As Google’s “Chief Internet Evangelist”, Vint Cerf is dedicated to expanding internet access globally.
- He sees AI as a transformative technology with a long history, and emphasizes its potential for positive impact.
AI in Crisis Response
- Google’s SOS alerts are being used in wildfire detection and warning systems in nine countries.
- AI is being trained to predict fire behavior, aiding in firefighting efforts and evacuations.
- DeepMind, an Alphabet company, uses machine learning to fold proteins, which could lead to breakthroughs in treating genetic diseases.
AI Literacy
- Cerf believes everyone should understand the basics of AI – its potential benefits and risks – even if they don’t know the technical details.
AI’s Future Impact
- Cerf envisions AI revolutionizing many areas:
- Enhanced research capabilities.
- Personalized tutors for every student.
- Powerful new creative tools for artists and filmmakers.
- Like the internet, AI is expected to become a vast platform for innovation.
- Hi, I’m Vint, vice president and chief internet evangelist at Google. Some people think of me as famous. I don’t. I think of me as lucky. I had the good fortune of
being the one of the people who started the design
of the internet in 1973. And since that time, my entire career has been strongly related to internet and its evolution. So people ask me, what is
a chief internet evangelist and why does the internet
need an evangelist at all? And the answer to that is that only about two thirds of
the world’s population are actually online and able to access all the treasures and
riches of the internet. And so, the chief internet evangelist is still running around the world, encouraging people to build more internet so everyone can have access. I’ve been around in the AI space for almost all of its existence because the notion of
artificial intelligence goes all the way back to the 1960s. So, let’s talk a little bit
about the way in which AI can be used in crisis situations like wildfires and things like that. In nine different countries, Google’s services are
being used, the SOS alerts, to detect and to alert
geographically about wildfires. So, we are starting to see raw material going into the artificial
intelligence algorithms to help us anticipate what
a fire is going to do. And that will help the
forest fire response and will certainly help
get people out of buildings if they are, in fact, at risk. Another example comes from one
of our sister organizations, DeepMind, which trained
a machine learning system to learn how to fold proteins that are generated by the
interpretation of DNA. And the reason that’s so important is that those molecules may turn out to be the key to solving various kinds
of genetic diseases. I mean, I get really excited
about stuff like that. AI literacy is really about
not the absolute details, exactly how does this work? Not everyone needs to know how a car is constructed to use it. We want people to have a conscious sense of both the power and peril
of artificial intelligence. I think in the long run, as we learn how to use these
techniques better and better and more reliably, that it
will have a dramatic impact on almost all walks of life. It will enhance our
ability to do research. Every student might have
a personal tutor, in fact. Creative people, who are
trying to create text and film, video and imagery,
will have a palette and a tool far more capable than a paintbrush in order to invent and create. And so, in the same way
that the worldwide web has turned out to be such a huge platform for creativity and innovation, I think the AI world will
induce a similar kind of effect.
Practice Assignment: Activity: Use AI to create a work email
Reading: Activity Exemplar: Use AI to create a work email
Reading
Completed Exemplar
To review the exemplar for this course item, click the following link and select Use Template.
Link to exemplar: Email prompt reflections (exemplar)
Assessment of Exemplar
Compare the exemplar to your completed activity. Review your work using each of the criteria in the exemplar. What did you do well? Where can you improve? Use your answers to these questions to guide you as you continue to progress through the course.
Note: The exemplar represents one possible way to complete the activity. Yours will likely differ in certain ways. What’s important is that you consider the capabilities and limitations of AI tools and recognize the importance of evaluating AI output.
Your Email prompt reflections template should include the following components:
- The Prompt section contains the initial prompt and the Output section contains the initial output.
- The Notes section presents a thoughtful evaluation of the conversational AI tool’s output. It lists three ways that the output meets the needs of the task, such as its kind tone and its thoroughness. It also lists three ways the output should be adjusted, such as by making the email more concise.
- The Observations section contains 3–5 sentences with observations about using a conversational AI tool to draft an email. For example, the reflection might suggest that it is easy to interact with the tool in a conversational way or that a potential workplace application is drafting other written content with the tool.