Day 6: AI in education, the good and the bad

Tuesday 7 May

Welcome to the final day of 6 days of AI. This last day of 6 days of AI is aimed at stimulating more discussion.

We have been looking at many ways we can use AI and its potential benefits. But of course, there are other considerations. Let us look at some of these considerations, there are four areas below.

1. What does Copilot think?

I asked Copilot to address the issue of AI in education, the good and the bad.

Certainly! Let’s explore the pros and cons of artificial intelligence (AI) in education:

The Good:

  • Personalization: AI tailors learning experiences to individual students, adapting content and pace.
  • Efficiency: Administrative tasks like grading and scheduling can be automated, freeing up educators’ time.
  • Innovation: AI enables interactive and engaging educational content, from virtual labs to adaptive quizzes.
  • Accessibility: AI tools can assist students with disabilities, promoting inclusivity.
  • Data-Driven Insights: Educators gain valuable insights into student performance and learning patterns.

The Bad:

  • Bias and Fairness: AI algorithms can perpetuate biases present in training data.
  • Privacy Concerns: Collecting student data for personalized learning raises privacy issues.
  • Job Displacement: Some fear that AI might replace certain teaching roles.
  • Ethical Dilemmas: Decisions made by AI systems require ethical scrutiny.
  • Overreliance: Balancing AI with human interaction is crucial for holistic education.

In navigating this landscape, let’s harness AI’s potential while safeguarding educational values and ethics.

So, do we think that Copilot has been biased in its assessment of the question?

2. Let’s look at the two paragraphs below

Carbon footprint

Training a GPT requires huge amounts of power and indirectly generates huge amounts of carbon, with important consequences for climate change. For example, it is estimated that the training of GPT3 (the GPT used by the first version of ChatGPT made available to the public) consumed 1,287 megawatt hours of electricity and generated 552 tons of carbon dioxide, the equivalent of 123 cars driven for one year.

Feedback loop

Another concern is that when future GPTs are trained, the data that they ingest are likely to include substantial amounts of text generated by previous versions of GPT. This self-referential loop might contaminate the training data and compromise the capabilities of future GPT models.

(Both texts from Introduction to Generative AI from UCL)

Do you feel that the two points above are substantial issues regarding the use of AI? Have you considered them? For all the positives of AI and the speed at which it is being incorporated into our lives, do we need to think more about other ways AI might be impacting on our lives?

3. Let’s consider the ethics of using AI

We often hear about the need to be cautious regarding AI – which is also often accompanied by images of Terminator and other AI humanoids such as Ex Machina. These concerns may certainly have a point and reason for us to be sceptical. Last year’s article in the Guardian by John Naughton, “‘A race it might be impossible to stop’: how worried should we be about AI?” highlights concerns that many people share, bearing in mind this article is nearly a year old, and things have moved on so quickly since then.

As part of Jisc’s exploration of artificial intelligence, they have created a free 'mini-MOOC', Should we be worried about AI?. If this is an area that interests you and you have half an hour to spare, this is a great place to start. You can split the course into four shorter chunks if you haven’t got a whole half an hour. There are new places released on the 1st of each month.

4. Further information

Educational Enhancement have set up a Padlet for ongoing information regarding key aspects of AI: University of Sussex AI Community of Practice: Teaching with AI.

There is key information on this Padlet from a variety of sources that you may find very interesting. It is updated frequently, so do bookmark this page to come back to it for regular updates.

For a student’s perspective on AI there was a very interesting student blog recently, The rise of AI: can we use it for studying? By Tugce Erten. The blog looks at both good reasons for using it as well as highlighting the dangers. A very balanced article while worth reading.

Your task for today: Give your feedback

Please feel free to give your feedback and answer the questions below using the 6 days of AI Padlet. There may be other issues or questions that you might want to explore. The aim of the discussion area is to get a variety of different opinions about AI. Many of our views about AI are still evolving and might change as we try out these new tools – you might just want to use this discussion area to test out some of your thoughts.

  • How did you get on with the task (reading through the four areas) – did you find the information useful?
  • Did you learn anything new?
  • Do you have any concerns regarding the use of AI in education?
  • Have you learnt more about AI since doing the 6 days of AI?

And lastly, we look forward to seeing you at the Festival of Sust(AI)nable Education conference tomorrow for an exciting day of discussions, stimulation and networking.

Please note: This course is designed to provide an introduction to the more popular AI tools. However, unless explicitly stated, the AI tools discussed are not supported or endorsed by the University of Sussex. All are free to use but may require users to provide personal information (e.g. name and email) to access.

Please DO NOT upload your own or others' personal or private data, INCLUDING STUDENT WORK, to any such unsupported tools. Doing so could be breach data protection regulations.

Acknowledgement

We would like to offer our thanks and acknowledge the University of the Arts London for inspiring us to create the 6 days of AI.

The 6 Days of AI is available under a Creative Commons License (CC BY NC SA) so it’s free to take, use and adapt for non-commercial purposes, if you acknowledge the source and share your version under the same licence.

You might also be interested in: