ChatGPT was launched by OpenAI in November and has attracted a wave of popular interest as never before in AI. George Siemens appeals for finding in the latest edition of his mail newsletter from Sensemaking, AI, and Learning (SAIL).
that middle space of sanity where technological innovation can be appreciated and implications on learners and society can be honoredSAIL newsletter
There seems to be a polarisation in the education community. The first is to lament and panic over what it means. The naysayers point to the threat it poses particularly to assessment. With a little coaxing ChatGPT can write very well versed essays and replies to traditional assessment assignments. hence the various calls to ban the use of ChatGPT from schools and colleges, to extend the use of the much hated (with reason) proctoring software applications or even to return to pencil and paper assessment exercises. I recall similar horror when calculators first came on the market! Yet for some years there have been many in the education community seeing this coming and advocating a move to authentic assessment.
The more positive reaction has been to see ChatGPT as a potentially beneficial tool for education. My own experiments have been in using ChatGPT for developing Open Education Resources. A Minnesota startup claims it has made the world's first online course that was created entirely by using artificial intelligence for developing a course on Artificial Intelligence
With single-sentence prompts ....the AI wrote an outline, all the lessons, and even found images and detailed videos about the subject. In all, the AI generated a full course made up of 19 lessons and a quiz.CBS Minnesota
I have been using ChatGPT to develop handouts and content for a Moodle short course on supporting students in developing their Personal Learning Environments. I asked ChatGPT "How can I use assessment for learning for assessing student work on developing their Personal Learning Environment."
The answer was:
Assessment for learning (also known as formative assessment) is a way of assessing students' progress and understanding during the learning process, rather than just at the end. It can be used to help students develop their personal learning environments (PLEs) by providing them with feedback on their progress and areas for improvement.
Here are some ways you can use assessment for learning to assess students' work on developing their PLEs:
- Use self-assessment: Encourage students to reflect on their own learning and progress by asking them to complete self-assessment activities, such as creating a learning plan or setting goals for their PLE development.
- Provide feedback: Give students regular feedback on their work and progress, including specific suggestions for improving their PLEs.
- Use peer assessment: Have students review and assess each other's PLEs, providing constructive feedback and suggestions for improvement.
- Use online tools: There are various online tools and platforms that can help you assess students' work and progress on developing their PLEs, such as learning management systems or online portfolios.
By using these and other assessment for learning strategies, you can help students develop their PLEs effectively and efficiently, and support their overall learning and development.ChatGPT
An approach to assessing students' progress and understanding during the learning process, rather than just at the end, is at least partly the way of overcoming the threat of AI to traditional end testing and is long overdue.
Our new European project, AI pioneers is geared at teachers and trainers inn vocational and adult education. The interesting thing here, is not just the implications and use of AI for teaching and learning but also the potential impact of AI on curriculum and learning content. AI has already been increasingly adopted in may sectors, and is developing new learning needs, not just for initial education but for existing skilled workers. And of course ChatGPT is just a sign of now AI is going to change working practices in many occupations.
The project will aims to directly address the issues of capacity, both systemic and institutional, through working with teachers and trainers, educational planners, stakeholders, and policy makers in Adult Education and VET, to
Produce recommendations, toolkits and implementation guidelines on the role and use of artificial intelligence.
To develop a sustainable approach to supporting the mainstreaming of AI in education
Identify, develop and pilot use cases of artificial intelligence in education and training including considering their impact on data, privacy, ethics and EU values.
Key to the project is to develop a community of practice - AI pioneers - of teachers and trainers around the use and development of AI in education. The term Pioneers is taken from the European DigCompEdu comptences for teachers and trainers in the use of technology for teaching and learning and is defined as follows: “Pioneers question the adequacy of contemporary digital and pedagogical practices, of which they themselves are Leaders. They are concerned about the constraints or drawbacks of these practices and driven by the impulse to innovate education even further. Pioneers experiment with highly innovative and complex digital technologies and/ or develop novel pedagogical approaches. Pioneers are a unique and rare species. They lead innovation and are a role model for younger teachers.”
Of course, questioning the adequacy of contemporary digital and pedagogical practices, includes attention to the concern over ethics. Many of the teachers and researchers we have worked with in the previous projects has raised concerns over data privacy and security. A second cause of concern was over bias and the non-transparency of algorithms. Another prominent issue was the lack of women involved in the growing AI industry. And with the EU reportedly set to regulate the use of AI, it is critical that not just researchers and experts but the ideas and concerns of practitioners form part of the regulatory rules and processes.
AI pioneers will use the existing Taccle AI website (to which this blog post is syndicated).
In the meantime, if you want to learn more here are four free newsletters covering AI and AI in education to which I subscribe:
OL Daily by Stephen Downes - As the name suggests a daily (and long running) newsletter on learning technology, new media, and related topics with regular updates on AI in education - Click here to subscribe
Sensemaking, AI, and Learning (SAIL) by George Siemens - free weekly newsletter focused on AI in education - subscribe
The Algorithm by MIT - free weekly newsltter from MIT Technology Review - Subscribe
The Algorithmic Bridge by Alberto Romero - newsletter about AI developments - more technical but interesting still - for free version subscribe here
Any suggestions of more resources is welcome - just use the Reply box.