Tuesday, 19 September 2023

AI as an intelligent tutor

AI as an intelligent tutor

Poh-Sun Goh

There will likely be a progressively increased role of AI as an intelligent tutor, providing individual feedback, as a scalable tool, educational and training assistant.

Goh, PS. Medical Educator Roles of the Future. (2020). Med.Sci.Educ. 30 (Suppl 1), 5–7. https://doi.org/10.1007/s40670-020-01086-w

Fazlollahi, A. M., Bakhaidar, M., Alsayegh, A., Yilmaz, R., Winkler-Schwartz, A., Mirchi, N., Langleben, I., Ledwos, N., Sabbagh, A. J., Bajunaid, K., Harley, J. M., & Del Maestro, R. F. (2022). Effect of Artificial Intelligence Tutoring vs Expert Instruction on Learning Simulated Surgical Skills Among Medical Students: A Randomized Clinical Trial. JAMA network open, 5(2), e2149008. https://doi.org/10.1001/jamanetworkopen.2021.49008 

St-Hilaire, Francois & Vu, Dung & Frau, Antoine & Burns, Nathan & Faraji, Farid & Potochny, Joseph & Robert, Stephane & Roussel, Arnaud & Zheng, Selene & Glazier, Taylor & Romano, Junfel & Belfer, Robert & Shayan, Muhammad & Smofsky, Ariella & Delarosbil, Tommy & Ahn, Seulmin & Eden-Walker, Simon & Sony, Kritika & Ching, Ansona & Kochmar, Ekaterina. (2022). A New Era: Intelligent Tutoring Systems Will Transform Online Learning for Millions. https://arxiv.org/abs/2203.03724




Friday, 4 August 2023

Adoption of AI in Health Professions Education

Adoption of AI in Health Professions Education

Poh-Sun Goh

"AI doesn’t take over jobs, it takes over tasks" quoted from "Generative AI: autocomplete for everything" 

by Noah Smith and roon, December 1, 2022


AI is another tool, that will form part of an educator's toolkit. An understanding of the Task at hand, before selection of the Tool for the Task is important. Start by defining the 'Job to be done' (Christensen et al, 2016). The Technology Acceptance Model, including the perceived ease of use and perceived usefulness of technology helps understand the adoption of AI in Health Professions Education (Sitthipon et al, 2022). 

Understanding the perspectives of stakeholders and users is important (Davenport & Glaser, 2022; Buabbas et al, 2023). Building digital literacy, and awareness of AI tools and capabilities - what is available and how to use it, will be an ongoing life-long learning and professional developmental process.

Ultimately Human plus AI will outperform AI or Human alone (De Cremer & Kasparov, 2021). Blending the best of Human Intelligence (HI) and AI.

References and Further Reading

Christensen CM, Hall T, Dillon K, Duncan DS. Know your customers’ “jobs to be done”. (2016)  https://hbr.org/2016/09/know-your-customers-jobs-to-be-done

De Cremer D, Kasparov D. AI Should Augment Human Intelligence, Not Replace It. (2021). https://hbr.org/2021/03/ai-should-augment-human-intelligence-not-replace-it



Sitthipon, Tamonwan and Kaewpuang, Pichart and Jaipong, Parichat and Sriboonruang, Patcharavadee and Siripipattanakul, Sutithep and Auttawechasakoon, Pichakoon, Artificial Intelligence (AI) Adoption in the Medical Education during the Digital Era: A Review Article (July 21, 2022). Review of Advanced Multidispliniary Science, Engineering & Innovation, 1(2), No.7, 1-7 (2022) , Available at SSRN: https://ssrn.com/abstract=4168693

Davenport, T. H., & Glaser, J. P. (2022). Factors governing the adoption of artificial intelligence in healthcare providers. Discover health systems, 1(1), 4. https://doi.org/10.1007/s44250-022-00004-8

Buabbas, A. J., Miskin, B., Alnaqi, A. A., Ayed, A. K., Shehab, A. A., Syed-Abdul, S., & Uddin, M. (2023). Investigating Students’ Perceptions towards Artificial Intelligence in Medical Education. Healthcare, 11(9), 1298. MDPI AG. Retrieved from http://dx.doi.org/10.3390/healthcare11091298








Wednesday, 12 July 2023

Artificial Intelligence in Higher Education Institutions

The use and development of technologies have transformed the world we live in. We have transitioned from a world of Web 1.0, where everything happened through a computer with dial-up internet connection, static portals, and the need for experts to establish an online presence. Later, users were empowered, and content creation was no longer exclusive to programmers. Nowadays, we all have the possibility to create content in various formats such as videos, audios, or texts, to name a few. We have the convenience of conducting financial operations remotely. The world has been evolving, and new ways of offering goods and services have emerged. The ultimate dream has always been for technology to take a step further and assist us with activities exclusive to humans.

While there are various Artificial Intelligence technologies, this post specifically mentions ChatGPT. Ever since ChatGPT, announced as the first Artificial Intelligence portal, was released for public use (with access restrictions in some countries), different industries have been embracing its use to gain competitive advantages and excel in their productive sectors. Educators at various educational levels are wondering about its application in education. OpenAI developed ChatGPT, which was launched in June 2020.

Padilla (2019) attributes the following characteristics to an intelligent agent:

1. Possesses mental attitudes such as beliefs and intentions.

2. Has the ability to acquire knowledge.

3. Can solve problems, even by breaking down complex problems into simpler ones.

4. Capable of performing complex operations.

5. Understands and can make sense of ideas.

6. Plans, predicts consequences, and evaluates alternatives.

7. Knows the limits of its own abilities and knowledge.

8. Can distinguish despite the similarity of situations.

9. Can be original, creating new concepts or ideas.

10. Can generalize.

11. Can perceive and model the external world.

12. Can understand and use language and its symbols.

But what is Artificial Intelligence?

The simplest answer to convey, as stated by Padilla (2019), is "the automation of activities that we associate with human thought processes, such as decision-making, problem-solving, machines exhibiting the same capabilities as humans."

ChatGPT is the first Chat Generative Pre-trained Transformer and was designed to generate responses and maintain conversations in the context of a chat or user interaction. Some industries are using AI for automation, information analysis, and pattern-based simulations.

Applications in the educational field, according to Vera (2023), include:

- Intelligent conversational agents

- Online platforms with personalized learning

- Processing large amounts of data

The integration of Artificial Intelligence represents a challenge but should also be viewed as a supportive tool to enhance learning experiences. From content delivery to activity development and assessment processes, teachers have a new ally. The next installment will delve further into this topic.

Juan Pablo Nigenda Alvarez

Traducido al inglés por ChatGPT


Padilla, R. D. M. (2019). La llegada de la inteligencia artificial a la educación. Revista de Investigación en Tecnologías de la Información: RITI, 7(14), 260-270.

Vera, F. (2023). Integración de la Inteligencia Artificial en la Educación superior: Desafíos y oportunidades. Transformar, 4(1), 17-34.

Sunday, 9 July 2023

Augmenting Human Intelligence with AI

Augmenting Human Intelligence with AI

Poh-Sun Goh

10 July 2023, 0807am, Singapore Time

AI is another way of augmenting human intelligence, human capability. We are all familiar with well tried and tested methods to gain new perspectives, deepen insights, and broaden our outlook, by reading around a topic, speaking to experts, attending conferences and courses, and getting formal training. AI is another tool to add to our toolkit.

Further reading

Markauskaite, Lina & Marrone, Rebecca & Poquet, Oleksandra & Knight, Simon & Martinez-Maldonado, Roberto & Howard, Sarah & Tondeur, Jo & Laat, Maarten & Buckingham Shum, Simon & Gasevic, Dragan & Siemens, George. (2022). Rethinking the entwinement between artificial intelligence and human learning: What capabilities do learners need for a world with AI?. Computers and Education: Artificial Intelligence. 3. 100056. 10.1016/j.caeai.2022.100056. 


Dimitriadou, E., Lanitis, A. A critical evaluation, challenges, and future perspectives of using artificial intelligence and emerging technologies in smart classrooms. Smart Learn. Environ. 10, 12 (2023). https://doi.org/10.1186/s40561-023-00231-3




Friday, 7 July 2023

Questions that technology solutions are doing regarding AI

 Questions that technology solutions are doing regarding AI

Mildred Lopez

This weekend I had the opportunity to attend Times Higher Education (THE) Latin America Universities Summit in partnership with Tecnologico de Monterrey. I participated in a networking session hosted by Turnitin https://www.turnitin.com/, and they posed three questions that I want to share with you:

Do you believe that the students using AI writing tools represent a challenge or an opportunity?

In my discussion table, we shared these arguments:

The challenge for teachers as they need to rethink the assignments in something more than writing an essay, as it can be easily generated with Chatgpt. 

The challenge for teachers is that to change their ways, teachers need training, and they need time and money. 

The challenge for institutions is that many priorities are battling for the same resources, such as teacher training and buying new platforms. 

It is an opportunity for teachers to use their time wisely in activities that add value for learners, for example, in mentoring rather than grading. 

It is an opportunity for programs to migrate from memorization to the application of knowledge finally.   

How do you integrate AI with teaching?

In developing educational resources that are adaptable to the interests and needs of learners.

In providing accurate and timely feedback for individual assignments, we can provide lots of input for classwork, and teachers can focus on the most complex projects where students create or propose ideas. 

As a teaching assistant, to curate content. 

What is the impact that writing with AI has on assessment?

It is making evident the problems we already hold regarding ethics and integrity. Although these are not new, it is harder to detect plagiarism or understand the percentage of the content generated by humans or AI. 

What do you think about these questions?


I do not hold any commercial relationship with the platform.  

Wednesday, 5 July 2023

Reflecting on current Learning and Work processes, and current limitations of AI

Reflecting on current Learning and Work processes, and current limitations of AI

Poh-Sun Goh

6 July 2023, 0337am, Singapore Time

Currently when making notes and preliminary reading and research around a topic I start by outlining what I currently know, and then sequentially and iteratively do key word online searches, reviewing topic and review articles, and further background and source material review. Then refine this material to the task at hand, and with a target audience. Current limitations of AI are the datasets it has been trained on, and the absence of dynamic, ongoing access and feedback (from human trainers) of the latest, topical and trending, as well as integrative work. My feel is that AI has a role as part of our toolkit, as one of several sources of information and assistance we might use, but with a clearly define role, and awareness of its limitations when, and if, we use AI, to assist, and augment our work.

Further Reading












Saturday, 1 July 2023

Beyond Chatgpt: AI resources for everyone


Beyond Chatgpt: AI resources for everyone

Mildred López

Recently, AI has been the buzzword everywhere. Even while grocery shopping, I overheard a discussion about AI where two clients in the fruit section were talking about this “Chagpt thing” supposedly taking over the world as it has a life of its own. AI is advancing rapidly; society needs to be involved in its development and the definition of management policies; however, AI is not only Chatgpt. There are many proposals that we can leverage to enhance our daily life and our medical education practice. I believe it is essential for us to explore the different uses to truly grasp what this is all about. 

1. PaLM - Google

The company uses PaLM 2 as the large generation model to power features such as Bard and the PaLM API. The proposal is to build AI with a responsible approach. 


You can learn more about it here:


2. Watson - IBM

It is a suite of technologies developed by IBM. It uses as well natural language format to interact with humans. 


It became famous in 2011 when it defeated humans on the TV’s Jeopardy! Family show. You can learn more about it here:


3. Chatgpt - OpenAI

It is a chatbot built on OpenAI’s platform to “get answers, find creative inspiration and learn something new.” 


Meet OpenAI CEO in this interview:


4. Azure AI – Microsoft

AI services for developers with access to vision, language, and speech analysis through learning models. 


These developments support many tools that can be incorporated for writing, generating images, etc. I’ll share a list with a few that I have collected, but feel free to share more in the comment section.


1. Grammarly: it is a writing assistance platform that enhances the grammar, spelling, tone, and pace of English writing. It can be used in documents, emails, and most websites.


2. Hypotenuse AI: content writer specialized in selling products, including the advantage of plagiarism check.


3. Sider AI: it has many tools within: summarizes articles, finds similar pages, explains any complex concepts, and compares answers between AI and humans


4. Wordtune: “Say exactly what you mean through clear, compelling, and authentic writing.”


Image and video generation

1. Synthesia: turns text into speech through more than 140 avatars and creates a video using AI. 


2. Gamma AI: creates documents, presentations, and webpages through prompts. The content that was generated can be edited through the platform or offline.


Chatgpt plugins.  https://openai.com/blog/chatgpt-plugins

1. AskYourPDF: share a document in a pdf format, and then Chatgpt can generate questions about that document. It can be powerful to help students review large quantities of data. 


2. Prompt perfect: a plugin that aids in crafting the best instructions for Chatgpt (or other. Language processors). 


What other developments, tools, and ideas have you tried? 

Learning and Training in the age of AI - going Micro, Macro and Meta

Learning and Training in the age of AI - going Micro, Macro and Meta

Poh-Sun Goh

Sunday, 2 July 2023, 0242am, Singapore Time

Having access to the world's knowledge (i.e. with access to the Internet), or an intelligent algorithm (i.e. AI or Artificial Intelligence), does not mean we have become more learned, become trained, more capable or skilled. Being able to look up an answer to how to do something online, or have an AI tool 'tell you' is only the starting point. 

Going Micro and Macro requires human assessment of both the answer(s), as well as its relevance to the question or task at hand, and its broader context. Going Meta includes human evaluation of underlying logic, and overarching principles and theory that might be relevant. Human input is particularly useful to do beyond surface answers to deeper considerations - from What and How, to Why and If.

There is value in figuring out the answer or how to do something compared to being given the answer or shown how. Discovery and exploratory learning activities opens the door to creative and new approaches to doing things. Not to mention deeper understanding and insight into why certain ideas and solutions were chosen, and implemented in a specific context.

Imagine the task of finding and fitting all the pieces to complete a picture puzzle. Whilst software and AI can accelerate the process of completing this task, there is value in examining and assessing each piece of the puzzle, fitting these together by trial and error, and progressively assembling the whole construct. When we are given an answer, and shown a solution, we lose the opportunity to explore and examine alternative and other avenues and ideas, and taking full advantage of questioning to learn. Fast and quick does not necessarily mean better or best - answer, idea, solution or path.

Further Reading







Weinstein, Y., Madan, C.R. & Sumeracki, M.A. Teaching the science of learning. Cogn. Research 3, 2 (2018). https://doi.org/10.1186/s41235-017-0087-y

Thursday, 29 June 2023

Myths and realities about AI

Myths and realities about AI

Mildred López

Yesterday, as I was preparing my daily reflection about Artificial Intelligence (AI), I did a simple search in Google for the prompt “artificial intelligence is….”. I’ll share with you a screenshot of the 10 first predictions that the search bar got me: 

Figure 1: Screenshot of Google search

These represent common myths or assumptions about AI. I would love for us to reflect together; therefore, I’ll share a video for each and my comments:

1. Artificial Intelligence is not prone to any bias or discrimination.

The reality is that it is prone to bias. The first step is to recognize them and build systems to address them. It is imperative that we understand how algorithms work and critically use the information it provides. 

See Jabril’s collab with CrashCourse shares 5 types of bias:

- Data reflects existing biases.

- Unbalanced classes in training data.

- Data doesn’t capture the right value.

- Data amplified by a feedback loop.

- Malicious data attack or manipulation.


2. Artificial Intelligence is dangerous. 

Define dangerous. I want to share with you the analysis of Joanna Stern in the Wall Street Journal. She used several challenges to see if AI with pass as a human. In several cases, it already passed:


3. Artificial Intelligence is going to take over our homes.

I am convinced it will get there, especially in monotonous tasks that can be automated. Tilman Wolff and Ranga Yogeshwar documentary for DW Documentary explains different applications, its pros, and cons:



4. Artificial Intelligence is about.

Listen to the excerpts of Stuart Rusell on Radio Davos:


5. Artificial Intelligence is a threat to humanity debate.

Beyond sci-fi movies, we need ground rules to work. Previous development rules for AI are no longer in place. Mo Gawdat (former Chief Business Officer for Google X) discusses with Piers Morgan the speed at which AI is learning. He mentioned 3 boundaries that they had for AI: 

- don’t put it on the open internet until the control problem is solved, 

- don’t teach it to code because that makes it self-develop,

- don’t have other agents prompting it.

I can’t forget one line of the interview where they mentioned, “I am not concerned of the machines…I am concerned of humans with AI in their hands”. You can see the full interview here: 


We need to focus not only on the rules for development but also on the implementation rules of these platforms. 

6. Artificial Intelligence is about mcq.

This prompt represents questions, multiple-choice questions about AI. It is a great opportunity to test our understanding of the topic. I’ll like to share a WIRED video of Gary Marcus, an expert on AI, answering questions from Twitter:


7. Artificial Intelligence is associated with computers of which generation.

The concept of generations of computers is explained briefly by Simply Coding at: 


8. Artificial Intelligence issues.

The Center for Humane Technology presents Tristan Harris and Aza Raskin, as they discuss the dilemma of AI development. See the full video at:


9. Artificial Intelligence is good or bad.

We cannot categorize it as good or bad. AI will work to do what we ask it to do, therefore, it depends on who is using it. See Janelle Shane TED conference on the danger of AI is weird than you think. She presents several examples for discussion.


10. Artificial Intelligence is defined as.

I enjoyed watching this video by Duke University; it leverages our understanding of pop culture, such as movies and series, to explain a complex concept in a relatable way:


What other myths and realities do you know about AI?


Explaining Artificial Intelligence in 5-levels of complexity

Explaining Artificial Intelligence in 5-levels of complexity

Mildred López (accompanied by Chatgpt)

I love the WIRED series that ask an expert to explain a complex concept in 5-levels of complexity; these allow me to analyze a concept from different perspectives. Here is an example: 


Today, I’ll attempt to do the same and explain Artificial Intelligence (AI) in 5 different ways. To do so, I received the help of Chatgpt. These prompts were used on June 29 at 5 pm at: 


For each, I'll share with you a shortened version of the responses for each level of complexity and the prompts that I used:

1. Artificial intelligence to a 10-year-old

Response of Chatgpt

Imagine you have a robot friend who can do things just like you, but it doesn't have a brain like yours. AI is a way to give that robot a brain so it can learn and make decisions by itself, just like humans do.

AI uses special computer programs to teach the robot how to do things. The robot learns from a lot of information, just like you learn from books and experiences. It looks at all the information, finds patterns, and uses those patterns to figure out how to solve problems or make choices.

For example, let's say the robot wants to recognize pictures of cats. You show it many pictures of cats and tell it, "These are cats." The robot learns what features or clues make something a cat, like pointy ears, whiskers, and a tail. Then, when you show it a new picture, the robot can decide if it's a cat or not based on what it has learned.


Explain artificial intelligence to a 10-year-old

2. Artificial intelligence to a teen

Response of Chatgpt:

Artificial intelligence is an exciting and rapidly advancing field of technology that focuses on creating computer systems that can perform tasks that usually require human intelligence. It's like teaching computers to think and learn just like humans do.

AI is all about building algorithms and models that enable machines to analyze data, recognize patterns, and make decisions. It involves training these machines on lots of information so that they can learn from it and become smarter over time.

One fascinating aspect of AI is machine learning. Machine learning algorithms allow computers to learn from examples and experiences, instead of being explicitly programmed for every specific task. Just like how you learn from practice and experience, AI systems get better at what they do with more data and training.


Explain artificial intelligence to a teen

3. Artificial intelligence to a college student

Response of Chatgpt:

Artificial intelligence is a fascinating field that focuses on creating intelligent machines capable of performing tasks that typically require human intelligence. It encompasses a wide range of techniques and technologies that aim to mimic or simulate human cognitive abilities using computers.

AI involves the development of algorithms and models that enable machines to process and understand information, learn from data, reason and make decisions, and interact with the world in meaningful ways. The goal is to create systems that can perceive, comprehend, and act in complex and dynamic environments.

Machine learning is a fundamental aspect of AI. It involves training computers to learn from data, allowing them to improve their performance on specific tasks without being explicitly programmed. Machine learning algorithms analyze patterns in data, identify relationships, and make predictions or classifications.


Explain artificial intelligence to a college student

4. Artificial intelligence to a college student

Response of Chatgpt:

Artificial intelligence is a multidisciplinary field that focuses on developing intelligent systems that can perform tasks requiring human-like intelligence. It encompasses various techniques, algorithms, and technologies that enable machines to perceive, reason, learn, and make decisions in complex and dynamic environments.

AI involves the creation of models and algorithms that allow computers to process and understand information, learn from data, and perform tasks autonomously. It aims to replicate human cognitive processes, such as perception, problem-solving, and decision-making, using computational methods.

Machine learning is a fundamental aspect of AI. It involves training computers to learn from data and improve their performance on specific tasks without being explicitly programmed. Machine learning algorithms can discover patterns, extract meaningful insights, and make predictions or decisions based on the learned information.


Explain artificial intelligence to a grad student

5. Artificial intelligence to an expert

Response of Chatgpt:

Artificial intelligence is a multidisciplinary field that focuses on creating intelligent systems capable of performing tasks that typically require human intelligence. It encompasses various subfields, including machine learning, deep learning, natural language processing, computer vision, and more.

At its core, AI is concerned with developing algorithms and models that allow machines to process and analyze data, learn from it, and make intelligent decisions or predictions. The goal is to enable machines to mimic or surpass human cognitive abilities, such as perception, reasoning, problem-solving, and decision-making.

Machine learning is a key component of AI, where algorithms learn from data and automatically improve their performance without being explicitly programmed. Supervised learning algorithms learn from labeled data to make predictions or classifications. Unsupervised learning algorithms find patterns in unlabeled data and discover hidden structures. Reinforcement learning involves training an agent to make decisions based on feedback from its environment.


Explain artificial intelligence to an expert on AI

Can you spot the differences? Do you think Chatgpt did a good job layering different styles to present the information? 


Curating Literature and Commentary on AI in HPE

Curating Literature and Commentary on AI in HPE

Poh-Sun Goh

Will be progressively curating, and selectively adding comments as part of an ongoing process to curate literature and commentary on AI in HPE.

Shankar, P. Ravi. Artificial Intelligence in Health Professions Education. Archives of Medicine and Health Sciences 10(2):p 256-261, Jul–Dec 2022. | DOI: 10.4103/amhs.amhs_234_22


Lomis, K., Jeffries, P., Palatta, A., Sage, M., Sheikh, J., Sheperis, C., & Whelan, A. (2021). Artificial Intelligence for Health Professions Educators. NAM perspectives, 2021, 10.31478/202109a. https://doi.org/10.31478/202109a

Gray K, Slavotinek J, Dimaguila GL, Choo D. Artificial Intelligence Education for the Health Workforce: Expert Survey of Approaches and Needs. JMIR Med Educ 2022;8(2):e35223. doi: 10.2196/35223


Jacob Krive and others, Grounded in reality: artificial intelligence in medical education, JAMIA Open, Volume 6, Issue 2, July 2023, ooad037, https://doi.org/10.1093/jamiaopen/ooad037

Dave, M., Patel, N. Artificial intelligence in healthcare and education. Br Dent J 234, 761–764 (2023). https://doi.org/10.1038/s41415-023-5845-2 ".. This article has been entirely written by the artificial intelligence (AI) software ChatGPT."

Ellaway, R.H., Tolsgaard, M. Artificial scholarship: LLMs in health professions education research. Adv in Health Sci Educ (2023). https://doi.org/10.1007/s10459-023-10257-4

Arbelaez Ossa, Laura & Rost, Michael & Lorenzini, Giorgia & Shaw, David & Elger, Bernice. (2023). A smarter perspective: Learning with and from AI-cases. Artificial Intelligence in Medicine. 135. 102458. 10.1016/j.artmed.2022.102458.  https://www.sciencedirect.com/science/article/pii/S093336572200210X

AI Describing AI - Being Meta About AI

 AI Describing AI - Being Meta About AI

Sol Roberts-Lieb

29 June 2023, 9:40am, Central US Time

As we know, artificial intelligence has the potential of changing our lives and education dramatically. The question is not if we should use it or not, but how and to what extent. How can we help our faculty, staff, and students understand the pros and cons of AI and what it means to them? 

Food for thought.  How does the use of AI extend beyond creating text to solve problems or provide answers? Where and how do we know what truth is when AI is used. 

The first set of images below was developed through Adobe Firefly. This is a new tool to turn text into art. 

Prompt: "Artificial intelligence in health professions education"


Questions: What does this mean to you? Does this encapsulate the prompt? Is this a work that I should get credit for even if I cite using Adobe Firefly?

The second image below was also developed by using Adobe Firefly. It is a description of my compared to an actual picture of me. 

Prompt: "a balding 46 year old Caucasian male weighing 300 pounds, six foot two inches in height with black hair, trimmed beard, and glasses. He is wearing a blue plaid shirt with khaki shorts. he is of Russian and Romanian descent"


Questions: While it isn't an exact match, it's close. How can we know what is AI and what isn't?

Share your thoughts with us. How doe these examples help us understand the use of AI in Education? 


Wednesday, 28 June 2023

Augmenting Human Intelligence - engaging in a broader discussion

Augmenting Human Intelligence - engaging in a broader discussion

Poh-Sun Goh

28 June 2023, 1120pm, Singapore Time

As we experiment with, and develop a feel of the role, and value add of Artificial Intelligence (AI), engaging in a broader discussion of how we augment human intelligence can be helpful.

Why do we learn? How do we learn? What do we do when we have a question? Or need to find out how to do something? At the workplace, or in social and recreational settings? Empirical observations, reflection on personal practice, and focused interviews at the workplace bring up common actions - i.e. which are to look it up online or in a guide, ask someone (e.g. a peer, more experience colleague, or expert), read around the topic and do background research, or get training (e.g. short course, or longer training program).

When we look something up online, background AI algorithms including autocomplete text options in the search box, and sections of common similar and related questions and answers, as well as online resources, articles and reviews are served up to us on the first page of answers, reflecting what has been found useful for others (by viewership, engagement, time spent, click throughs and recommendations/citations). As we engage further with online content, background AI algorithms designed to keep us online will continue to refine what the search engine and online pages present and serve up to us. In this way, we are already taking advantage of AI, either consciously or unconsciously, on a regular basis, whenever we look something up online on a search engine, and progressively engage with content. This process mimics what happens when we 'ask someone', a peer, or experience colleague. In the case of online searches the process is massively scaled up taking advantage of a large pool of previous and ongoing topic searches, progressively refined by our further search and engagement behaviour. 

Embedded co-pilot AI within familiar professional and productivity software, and mobile Apps can potentially increase our productivity, by offering us first cut templates, initial drafts, and suggestions, drawn from what these AI models and tools have been trained on. As human users we then add individual and specific task based customisation and personalisation. Where and how AI adds value, and understanding how, when and to what extent we use AI will be an ongoing, iterative process. As we seek to get the job done, as efficiently and effectively as possible. Ultimately AI is simply another tool in our toolbox or toolkit. To be used, or not. Depending on what we need to do, and what the situation demands. 

Further Reading

Christensen CM, Hall T, Dillon K, Duncan DS. Know your customers’ “jobs to be done”. https://hbr.org/2016/09/know-your-customers-jobs-to-be-done. Accessed 28 June, 2023.

Gartner Hype Cycle. https://www.gartner.com/en/research/methodologies/gartner-hype-cycle. Accessed on 28 June 2023.

Goh, PS. Medical Educator Roles of the Future. (2020). Med.Sci.Educ. 30 (Suppl 1), 5–7. https://doi.org/10.1007/s40670-020-01086-w

Goh, PS. (2021). 'The vision of transformation in medical education after the COVID-19 pandemic'. Korean J Med Educ. 33 (3): 171-174. https://doi.org/10.3946/kjme.2021.197