For those training to teach, or training for anything for that matter, AI might seem to offer an easy option for fast access to information and the knowledge often needed before a next step can be taken. Take a trainee (or even experienced) teacher who is teaching about a certain topic for the first time.  Let’s imagine that ‘topic’ involves learning how to write a story setting and let’s imagine that it’s for a Year 3 class. And now let’s imagine I instructed the increasingly popular ChatGPT to ‘Give me a lesson plan for Year 3 about writing a story setting’. In fact don’t just imagine that bit - I did it and so could you - and within seconds it gave me a ‘passable’ lesson plan. The question is, would I consider it only ‘passable’ without a couple of decades of teaching behind me? (Answer: possibly not as I might not know better.) I could also ask (or should also ask) ‘How can this be made better?’ and ‘How will it benefit my pupils?’ and ‘What else do I need to know?’ (but I probably wouldn’t if I was inexperienced and looking for a quick win).

 

What my request had delivered didn’t give me anything other than a basic example of a setting description, and nothing more than a lesson structure and steps to involve the children in considering some vocabulary and having a go at describing a picture of a setting. All fine, of course, but without experience it’s hard to add depth and breadth. Would I know what to consider in terms of the prior learning, in terms of the requirements of the National Curriculum, in terms of the ability range of the class, and so on. And what about the pedagogy? What is to say that the ideas put forward are the best for my class, or the best for me? 

 

 

Could a novice pick-up that lesson and make it ‘work’ - yes potentially - after all, I did call it ‘passable’. And could the same novice create many more ‘passable’ lessons for a whole range of subjects in the same way? Absolutely - I’ve tried it and AI delivers. But will the novice be able to deliver to a high standard with over-reliance on AI? I think the answer to that question is at best embedded in the realms of ‘very doubtful’.   Considering why you might use a certain technique and not another, and how a lesson fits into the bigger picture, and why the children are grouped in a particular way, and what adaptations could be made at any point in the lesson to scaffold or challenge or reframe ideas, are just a small part of a long list of what makes planning and teaching more than just ‘passable’. Observations of, and discussions with, experienced mentors and teachers, help develop knowledge and understanding of how to weave together the many strands of teaching to make teaching and learning as effective as possible in enabling learners to become increasingly secure in their own knowledge, skills and understanding. The novice teacher needs to build their own experience through their Initial Teacher Training, early experience and interactions with the Early Career Framework, and that’s just as a starting point in their career.

 

Maybe that’s what AI generated lessons can or should also be - a starting point.  It can be used to get the nub of an idea, and used to help us with initial knowledge if we’re not secure with something we’re trying to teach but at this point in time it’s hard to argue against the fact that the art and science of teaching and learning develops with experience. By all means use AI to generate information to supplement developing  experience and knowledge, but beware of anything that sounds too good to be true. Artificial Intelligence promises and encompasses so much. It  is clearly causing huge concerns in society - deep fake videos, voice imitation, fake pictures and so on make people wary. And we should be. But we don’t necessarily need trust issues at a basic level - what we need is the teaching experience in the first place to help us to be as discerning as possible with the information with which we are presented. Gaining that experience, including the highs and lows of great successes and miserable mistakes, is a huge part of what makes teachers successful. This includes us considering the issues that might exist when using AI for lesson planning, so to close this blog post here’s something directly from ChatGPT itself - a list of points well-worth considering.

 

                                                                                                                                          

 

What are the issues with novice teachers using AI for lesson planning?

Novice teachers using AI for lesson planning can face several challenges and issues. These include:

  1. Over-Reliance on Technology: Novice teachers might rely too heavily on AI-generated content, which can hinder their development of essential teaching skills, such as curriculum design and critical thinking about lesson content.
  2. Lack of Customization: AI tools might not fully understand the unique needs of a specific classroom, including students' individual learning styles, cultural backgrounds, and specific educational goals. This can result in lesson plans that are not tailored to the needs of the students.
  3. Quality and Accuracy: AI-generated lesson plans might sometimes lack depth, be too generic, or contain inaccuracies. Novice teachers may not yet have the experience to identify and correct these issues.
  4. Ethical Concerns: Using AI tools involves data privacy and security concerns, especially when sensitive student information is involved. Novice teachers may not be fully aware of these ethical considerations.
  5. Teacher Autonomy and Creativity: Relying on AI for lesson planning can limit a teacher’s creative input and professional autonomy, potentially stifling innovative teaching methods and personalized approaches to education.
  6. Technical Skills and Comfort: Novice teachers may not be fully comfortable or proficient with the technology, leading to frustration and ineffective use of AI tools.
  7. Dependence on AI Updates and Maintenance: AI tools require regular updates and maintenance. Novice teachers might not have the knowledge or resources to manage these aspects, leading to disruptions in their lesson planning process.
  8. Pedagogical Soundness: AI-generated lesson plans might not always align with best pedagogical practices. Novice teachers might not have the expertise to critically evaluate and adapt these plans to ensure they meet educational standards and objectives.
  9. Reduced Engagement with Educational Content: By outsourcing lesson planning to AI, novice teachers may miss out on the deep engagement with content that is necessary to fully understand and teach a subject effectively.
  10. Professional Growth: The process of lesson planning is crucial for professional growth. Over-reliance on AI can impede the development of important skills such as classroom management, assessment design, and reflective practice.

Addressing these issues involves providing novice teachers with adequate training on how to effectively integrate AI tools into their teaching practice while maintaining a critical and reflective approach to their use.

OpenAI's ChatGPT. (2024, May 30). Personal communication.

 

 

Jon Goulding

Lead Mentor