Upskilling With AI: Part 1

“Upskilling” is the idea of a person gaining new skills for the purpose of giving and getting service better. Service is the application of resources (e.g., knowledge) for the benefit of another. Businesses help their employees upskill to improve their offerings to customers. Universities help students upskill to become better future citizens and employees. Even government policymakers create programs to help citizens upskill for the high-skill, high-pay jobs that often drive economic development for improved quality-of-life.

Why is upskilling with AI important? Service providers will not be replaced by AI, but trusted service providers who use AI (well and responsibly) will replace those who don’t. Everyone with a role in an organization is a service provider.

What is the good news about upskilling with AI? The good news is that it is really easy to get started using AI tools, and to begin upskilling. Today’s AI tools can help people quickly get started on a range of tasks from writing about a topic to creating artwork to accompany written text.

What is the bad news about upskilling with AI? The bad news is today’s AI tools are still at an early stage, and make a lot of mistakes. The statistical models of the world that exist in AI tools today have many technical limitations [1]. These limitations can and will give rise to a wide range of harms and social problems [2]. These limitations require the user to take responsibility for understanding the limitations, staying away from unethical and improper use of the tools, and a range of other considerations [3]. Of course, AI tools will get better over time – which will create additional potential benefits and harms [4].

Example: Using AI tools

A good place to start learning to upskill with AI is by trying out two AI tools from OpenAI, called ChatGPT (create an essay from a topic prompt) and DALL-E (create a picture from a topic prompt). Within two months, ChatGPT had achieved 100 million users.

Below is an example of what is possible, for example on the topic of “Upskilling with AI.”

Date: Tuesday, January 17, 2023
Dear, Jim. I thought it would be great to have a short guest article piece (300- 500 words max) on the topic of upskilling with AI. We are in the midst of uncertainty when many organisations these days are downsizing and laying off people while economists anticipate that the world economic growth will slow down in 2023. I think it would be nice to get some insights into how we could stay resilient by upskilling with AI. Thanks, Cecilia

Date: Friday, February 10, 2023

ChatGPT Prompt: I thought it would be great to have a short guest article piece (300- 500 words max) on the topic of upskilling with AI. We are in the midst of uncertainty when many organisations these days are downsizing and laying off people while economists anticipate that the world economic growth will slow down in 2023. I think it would be nice to get some insights into how we could stay resilient by upskilling with AI.

ChatGPT Output: Upskilling with AI: Staying Resilient in Uncertain Times

In today’s rapidly evolving job market, AI is one of the fastest-growing industries and it’s transforming the way we work, live and interact. In the midst of uncertainty and economic slowdown, upskilling in AI has become increasingly important for professionals to stay relevant and competitive in the job market.

AI is a vast field that encompasses a wide range of technologies, including machine learning, computer vision, natural language processing and robotics. Learning these cutting-edge technologies not only allows individuals to gain valuable knowledge, but also enhances their technical skills, making them highly desirable in the job market.

One of the benefits of upskilling with AI is that it can lead to new career opportunities. With the increasing demand for AI professionals, individuals with AI skills are likely to find new and better job opportunities, even in times of economic slowdown. Moreover, upskilling with AI can open the doors to new fields, such as data science, machine learning engineering, or AI product management.

Another advantage of upskilling with AI is that it can increase an individual’s earning potential. AI professionals are in high demand, and as a result, they tend to command higher salaries compared to those without AI skills. Upskilling with AI can help individuals increase their marketability and make them more attractive to potential employers, thereby increasing their earning potential.

Upskilling with AI is also a way to increase job security. As AI continues to change the way we work, there is a growing concern that it will displace certain jobs. However, upskilling with AI can help individuals stay ahead of the curve and be prepared for the future of work. It can help individuals transition into new roles or industries and increase their job security.

There are several ways to upskill with AI, including online courses, certification programs, and workshops. Many universities and online platforms now offer courses and programs specifically designed for AI upskilling, and they are accessible to individuals at any stage of their careers. Additionally, participating in hackathons, attending AI conferences, and engaging with AI communities can also provide opportunities for individuals to learn, grow and network with AI professionals.

In conclusion, upskilling with AI is a way for individuals to stay relevant, competitive, and secure in today’s job market. With the rapid pace of technological change, upskilling in AI has become increasingly important, and it’s never too late to start. Whether you’re a recent graduate or a seasoned professional, there are plenty of opportunities to upskill and grow your career with AI.

Creating Picture:

After ChatGPT created the above essay, I asked ChatGPT to create a good prompt for DALL-E to create a picture to accompany the article. The images below provide specifics.

Creating a short essay using ChatGPT

Creating a picture with DALL-E

Creating a second picture with DALL-E

DALL-E generates four pictures, and the user can choose the best of the four, and then the user has to add the text manually to the picture.

Because I wasn’t fully satisfied with the first picture, I asked ChatGPT to create a second DALL-E prompt, and show the second prompts results as well. Using AI tools to create essays and pictures from prompts is sometimes called “prompt engineering.” Prompt engineering is somewhat like learning to ask good questions. Prompt engineering is just one of the skills to learn when using certain AI tools, and it takes a great deal of practice to become good at it. Also, because AI tools often generate factually incorrect material (large AI models are trained on both fact and fiction, as well as both historical text and speculations), it is important to learn “verification techniques” as well – to ensure accuracy of information in the essays.

Concluding Remarks: Getting Real

By the way, to see the actual blog post and pictures that I used in the ISSIP Newsletter, which are quite different from the above, check out the February 2023 ISSIP Newsletter here [5]. You can judge which you think is better, the one that ChatGPT wrote in about 1 minute, or the actual one that I wrote which took about 30 minutes. Someday when I have a digital twin trained up on all my writings and my life experiences narrative, a future AI tool might be able to write something much better.

References

[1] Stephen Wolfram (2023) What Is ChatGPT Doing … and Why Does It Work? URL: https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/

[2] Gary Marcus (2023) Two frightening things before breakfast. URL: https://garymarcus.substack.com/p/two-frightening-things-before-breakfast

[3] Ethan Mollick (2023) The future, soon: what I learned from Bing’s AI. URL: https://oneusefulthing.substack.com/p/the-future-soon-what-i-learned-from

[4] Elizabeth Weil (2023) You Are Not a Parrot. And a chatbot is not a human. And a linguist named Emily M. Bender is very worried what will happen when we forget this.
https://nymag.com/intelligencer/article/ai-artificial-intelligence-chatbots-emily-m-bender.html

[5] Jim Spohrer’s actual blog post on “Upskilling with AI” in the ISSIP Newsletter
https://us7.campaign-archive.com/?u=d0f540537d3ef307e062e3dd6&id=c409413dfe