In November 2022, ChatGPT was launched. The prototype generative Artificial Intelligent tool grew to more than 100 million users by January 2023 making it one of the most quickly adopted tools. The implication that this has had across sectors is significant with many headlines concerning education practices. Plagiarism and essay mills have long been a concern for educators, but now AI tools are testing regulations and similarity detectors globally.
One of the first scholarly works to address the implications for ChatGPT in education was published in April 2023. Baidoo-Anu and Owusu Ansah (2023) address the
benefits, recognised by many in the sector, around personalised and interactive learning, generating prompts for formative assessment and providing feedback. The concerns around misuse have dominated much of the media narrative with headlines warning, “Is AI a threat to HE?” . Writing coach, Peter Laffin, was cited in a news report with his concerns that ChatGPT “will lead to a crisis in learning, forcing educators to rethink schooling entirely.”. These arguments have provided a sense of scaremongering, which have been common practice in the discourse of technology and the effects it can have on a younger generation. There are concerns with generative AI, particularly around bias, privacy and false information but instead of banishing the technology, educators need to be asking how it can be used “safely, effectively and appropriately” (Connolly and Watson 2023).
Discussions are ongoing in working groups and task forces at many institutions to understand how ChatGPT can enable better working, efficiencies and increase participation and engagement in teaching and learning. Prior to this, it is essential to focus on literacies. In my recent book, we discussed the need for a new literacy concerning immersive media to fully understand the technology to allow critical engagement and maximise its potential. Just as we presented an argument and concept for understanding literacies of virtual and augmented reality, now is the time to focus on the critical usage of AI tools and for that, a new literacy must emerge.
I used ChatGPT to generate the need for literacy and what that would look like. The initial prompt was, “what does it mean to be AI literate?”. The response generated was:
“To be AI literate means having a basic understanding of what artificial intelligence (AI) is, how it works, and what its potential applications and implications are. It involves being able to understand and communicate about AI concepts and technologies, as well as being able to critically evaluate and assess the impact of AI on society, including ethical and social issues. Being AI literate also means being able to identify and utilize AI tools and applications in relevant domains, such as data analysis, natural language processing, and computer vision. AI literacy is becoming increasingly important as AI continues to transform many industries and aspects of daily life.”
I added a further prompt, “how do I become AI literate?”, in which a series of bullet points were produced.
“Becoming AI literate involves learning about various aspects of AI and its applications, as well as developing critical thinking and analytical skills to assess the impact of AI on society. Here are some steps you can take to become AI literate:
1. Learn the basics: Start by understanding what AI is and how it works. Familiarize yourself with terms such as machine learning, deep learning, neural networks, and natural language processing. You can find introductory materials online, including tutorials, videos, and online courses.
2. Study AI applications: Explore different applications of AI, such as computer vision, speech recognition, and data analysis. Understand how these applications work and how they are used in different industries, including healthcare, finance, and transportation.
3. Develop analytical skills: Learn how to analyze and interpret data using AI tools and techniques. Understand the strengths and limitations of different AI algorithms and methods.
4. Explore ethical and social issues: Consider the ethical and social implications of AI, including issues such as bias, privacy, and security. Learn about different approaches to addressing these issues.
5. Stay up-to-date: Keep up with the latest developments in AI by reading news and research articles, attending conferences and workshops, and engaging with the AI community online.
6. Practice using AI tools: Experiment with AI tools and technologies, such as machine learning platforms or chatbot builders, to get hands-on experience with AI.”
For each of the six bullet points, I added a prompt to go deeper. As an example, “can you help me learn the basics?”
“Of course! Here's a brief overview of each term:
1. Artificial Intelligence (AI): AI refers to the ability of machines or computer programs to perform tasks that typically require human intelligence, such as recognizing speech, understanding natural language, making decisions, and recognizing objects in images.
2. Machine Learning (ML): Machine learning is a subset of AI that involves training computer algorithms to learn patterns from data, without being explicitly programmed. ML algorithms can improve their performance over time by learning from the data they process.
3. Deep Learning: Deep learning is a subset of ML that involves training artificial neural networks with multiple layers to learn complex patterns from data. Deep learning has been particularly successful in applications such as image and speech recognition.
4. Neural Networks: Neural networks are a type of ML algorithm that are inspired by the structure and function of the human brain. They are composed of interconnected nodes or "neurons" that process and transmit information.
5. Natural Language Processing (NLP): NLP is a subset of AI that involves teaching machines to understand and generate human language. NLP is used in applications such as chatbots, voice assistants, and machine translation.
To become more familiar with these terms and concepts, I would recommend starting with some introductory online courses, such as those available on Coursera, Udemy, or edX. You can also find many free resources online, such as blogs, videos, and tutorials. By practicing with these concepts, you can begin to understand how they are used in real-world AI applications.”
One of the biggest challenges facing educators and users of ChatGPT or other generative AI tools, are social and ethical issues. The response was generic and expected when asking ChatGPT to “help me understand the ethical and social issues with AI”.
“Here are some of the ethical and social issues associated with AI:
1. Bias and discrimination: AI algorithms can perpetuate bias and discrimination if they are trained on biased data or if they reflect the biases of their developers. This can lead to unfair treatment of certain groups of people and reinforce societal inequalities.
2. Privacy and security: AI algorithms can collect and process large amounts of personal data, raising concerns about privacy and security. There is also a risk of malicious actors using AI to conduct cyberattacks or to exploit vulnerabilities in systems.
3. Transparency and explainability: Many AI algorithms are black boxes, meaning that it is difficult to understand how they arrive at their decisions or recommendations. This lack of transparency and explainability can make it difficult to assess their accuracy, fairness, and ethical implications.
4. Job displacement: AI has the potential to automate many jobs, which could lead to job displacement and the need for retraining or reskilling.
5. Accountability and responsibility: As AI becomes more autonomous, it raises questions about who is responsible for its actions and decisions. This can create challenges in assigning accountability and liability for any harm caused by AI.
6. Social impact: AI can have both positive and negative impacts on society, ranging from improved healthcare and education to the exacerbation of existing social problems, such as wealth inequality and political polarization.
It is important for individuals, organizations, and policymakers to consider these ethical and social issues when developing and implementing AI technologies. By addressing these issues proactively, we can ensure that AI is developed and used in a responsible and beneficial way.”
With much debate about its use in education and the generational gap in using and being familiar with technologies, I prompted ChatGPT to determine whether AI literacies are different for adults and children. A less generic and perhaps more artificially considered response was provided:
“Yes, the approach to becoming AI literate can be different for adults and children, as their backgrounds, interests, and learning styles may differ. Here are some considerations for each group:
For adults:
· Adults may have more prior knowledge and experience with technology and may prefer a more self-directed approach to learning about AI.
· They may benefit from more in-depth and technical resources, such as online courses or textbooks.
· Adults may have a particular interest in how AI is changing their industry or profession and may want to focus their learning in that area.
For children:
· Children may benefit from more interactive and engaging learning experiences, such as games, simulations, or hands-on projects.
· They may need more scaffolding and guidance in understanding the technical aspects of AI and its applications.
· Children may be particularly interested in AI applications related to topics they are studying in school, such as natural history, physics, or history.”
To conclude, the need for an AI literacy is evident, as the technological capabilities increase at a fast pace. It is critical to do this work now so that the technology can be utilised to its full potential, without banishing it simply as a concern. Generative AI can have deep impact on the teaching and learning experience. It can provide efficiencies and enable a personalised experience that will promote engagement. This can only be done if we work to ensure we are critical users of the technology, understanding its limitations and pushing it to achieve the opportunities. The final words from ChatGPT.
“In summary, a person with a good level of AI literacy would have both a theoretical and practical understanding of AI, as well as a broad perspective on its social and ethical implications. They would be able to communicate effectively about AI with both technical and non-technical audiences, and would be well-positioned to work in a variety of industries that are using AI to drive innovation and growth.”
Comments