Another of our intermittent blogs during the #AARE2022 conference. If you want to cover a session at the conference or want to respond to something you’ve heard, please email email@example.com to check in. Thanks!
George Siemens gave the 2022 AARE conference keynote speech yesterday morning and the takeaway was this: artificial intelligence (AI) is already changing education in Australia whether we’re ready for it or not. He went on to suggest that unless we’re mindful we, as researchers and teacher educators, may not have a seat at the table in deciding what the future of education will look like. This blog post is about the future of AI-generated lesson plans and how we might think about this development today and into the future. Think of it as a concrete case study of exactly what George was talking about this morning where the conclusions might apply to other areas of education
What do today’s AI-generated lesson plans look like?
AI-generated lesson plans are already better than many people realise. Here’s an example generated through the GPT-3 deep learning language model:
Prompt: A lesson plan for English for teaching 16 year old students about the idea of “juxtaposition” within Romeo and Juliet.
Output from GPT-3 (verbatim, with formatting provided by the algorithm):
Juxtaposition is the act of placing two things side by side, often for contrast. In literature, authors often use juxtaposition to create a certain mood or atmosphere, or to emphasize certain qualities of a character or situation.
In Romeo and Juliet, Shakespeare uses juxtaposition extensively to contrast the two lovers and their families, the Montagues and the Capulets. He also uses juxtaposition to contrast the tragic events of the play with the light-hearted moments.
By the end of the lesson, students will be able to:
– Understand the concept of juxtaposition
– Identify examples of juxtaposition in Romeo and Juliet
– Explain how juxtaposition is used to create mood and atmosphere in the play
– A copy of Romeo and Juliet
– A whiteboard and markers
– A teacher-created handout with examples of juxtaposition from the play (optional)
1. Introduce the concept of juxtaposition to the class. Explain that authors often use this literary device to create contrast and emphasize certain qualities.
2. Ask the students to think of an example of two things that are often juxtaposed. Write some of their responses on the board.
3. Tell the students that they are going to be looking for examples of juxtaposition in Romeo and Juliet. Explain that they should pay attention to how the contrast created by the juxtaposition contributes to the mood and atmosphere of the play.
4. Give the students time to read through the play, or assigned sections of the play if time is limited. As they are reading, they should be looking for examples of juxtaposition.
5. Once the students have finished reading, ask them to share the examples of juxtaposition that they found. Write these examples on the board.
6. Finally, ask the students to explain how the juxtaposition affected the mood and atmosphere of the play. What did it emphasize about the characters or the situation?
Have the students find additional examples of juxtaposition in other works of literature, or in everyday life. They can share their examples with the class and explain how the contrast created by the juxtaposition contributes to the overall effect.
Imagine that you’d set a task for a class of second year Bachelor of Education students to create a lesson plan with that same prompt. How do you think the AI response would compare to some of your students?
Anybody can generate their own lesson plans for a year level, subject area, and topic that interests them with a similar prompt: https://beta.openai.com/playground
It is trivially easy to generate useful lesson plans using this technique. One obvious upshot is that setting assessment tasks for any students in initial teacher education that involve them creating lesson plans isn’t a great idea any more—it’s too simple for them to generate one. Yet there are new opportunities that arise:
- Why not get students to generate a few lesson plans, look at the patterns, and write something about the essential structure of this thing that we call a ‘lesson plan’?
- Why not get them to take a generated lesson plan and improve it, annotating the reasons why their changes have made it better?
Another legitimate concern that arises is that inservice teachers might start to use the next generation of AI-generated lesson plans (which will undoubtedly be an order of magnitude more powerful) without critique—or worse, that some jurisdictions might actually request that teachers use such an approach in future.
A word that we need to look to is “design”
The issues raised by AI regarding lesson plans and in many places in education too can be addressed by consideration of design. When design in education is done well (whether that’s learning by design, design thinking, co-design, or within the subject area named “design”) it always places an emphasis on two things:
- Authentic problems: such that the learner must always construct an interpretation of the problem before they can address it
- Process and rationale such that the output that the student produces is impressive only if their process and rationale support what they’ve done.
When assessments follow these two ingredients then educators can give students free rein to use whatever tools they have at their disposal. The adoption of AI stops being a concern. When students are being assessed through their process rather than their output, students can use whatever tools are available. The challenge is integrating use of such tools into solving problems through collaboration, critical thinking, cultural understanding, and creativity.
Design as a response to “what should be taught”
George Siemens concluded his presentation by suggesting a list (controversially) of what should be taught in the context of an AI future. A summary/interpretation of his key points of what we should be teaching is:
- Beingness: what it means to be human in the world, the interconnectedness of all things
- Systems thinking: how systems change and what complexity is about
- Technology and how to use it: machine learning and data literacy, computational thinking, collaborating with non-human intelligences
Increasingly, design has become a part of education: design for learning, learning by design, thinking, and so on. The epistemic fluency to design using computational tools in a way that enriches material life and human culture is at the root of all three of these areas.
For any subject area, teaching using a design approach shifts the focus from knowing content to knowing process. It becomes less about how to get from A to B in a straight line and more about knowing how to frame problems, use tools, and communicate outcomes. More design in education provides one way of responding to this increase presence of AI in education, whether we’re ready for it or not.
It might even provide a response to George’s provocation about McKinsey, Deloitte, or Microsoft trying to get in on a slice of the education sector. Education conceived as design—process rather than output—prioritises the humans involved in the enterprise and makes it harder to sideline educators.
Dr Nick Kelly is a Senior Lecturer in Interaction Design at the Queensland University of Technology, in the School of Design. He is a genuinely cross-disciplinary researcher spanning the fields of Design and Education. He conducts research into design cognition (how designers think), metacognition in learning (how teachers and learners develop their metacognitive abilities), and places where these two things come together (design pedagogy, design for learning, learning by design, design of learning technologies). His specialisation is in the design, facilitation, and analysis of online communities.
Dr Kelli McGraw is a Lecturer in the Faculty of Creative Industries, Education Social Justice at QUT. Currently teaching units in Secondary English curriculum, pedagogy and assessment, her prior experience includes teaching high school English and debating in Southwest Sydney, NSW. Kelli researches the fields of English curriculum studies, secondary school assessment, teacher identity, digital literacy, popular culture and new media texts.