As I look back on my first trimester as a Lecturer in Education Studies, I am filled with a deep sense of gratitude. After working for a decade in Higher Education in various capacities, transitioning to an academic role has been a refreshing and rewarding experience. In this blog post, I would like to share my reflections on the first six months of my journey as a lecturer. I’ll delve into my interactions with students, my growth as an educator, and my anticipation for the future. This long overdue post continues the blog series I’ve written reflecting on my new career.
While I am not new to the University or education, in moving from Learning Development to Education Studies, I am joining a new community of practice (Wenger, 1998). I still feel I have a lot to learn in this broader field, and I have supplemented my academic memberships to include the British Educational Research Association. I’m also renewing my efforts to get involved with the Society for Research into Higher Education, as well as retaining my scholarship of learning development via ALDinHE.
The student community
One of the most significant highlights of my teaching experience has been the connection with my students. I’ve commented on this multiple times before, but their enthusiasm, curiosity, and dedication have been genuinely inspiring, and it represents something I didn’t get as a Learning Developer – at least not in a sustained way. As a lecturer, I have thoroughly enjoyed witnessing my students’ creativity, especially during workshops and from marking written assessments. Reading their reflections has not only allowed me to observe their growth but, thanks to the international nature of my students, it has also provided me with valuable insights into other places on the planet. As I further integrate into the School of Education, my interactions with students have fostered my understanding of their needs, which I can now better address in the planning and delivery of my teaching. This is refreshing also – as I speak to a consistent audience, education. No need to wear multiple hats as a Learning Developer.
Personal and research supervision have been very new aspects of my role. While I encountered pastoral issues in Learning Development, it was not part of the remit and so I would always refer the student to student support services and personal supervisors. As a Learning Developer, I actively supported research but never had the deciding role. As a Learning Developer, I would muse on ethical issues with students; I am now signing off applications as an academic. This was the kind of challenge I needed. Teaching has been a staple of my career as a Learning Developer, but there are new things to learn and do as a supervisor.
I have found personal supervision to be a surprisingly fulfilling aspect of my new role. Engaging in one-on-one discussions with my students has allowed me to establish a deeper connection with them and provide targeted guidance tailored to their individual needs (Knowles et al., 2014). Personal supervision sessions have led to many meaningful conversations, enabling me to better understand the challenges and aspirations of each student.
Research supervision has been really rewarding with my undergraduates. Although I am only supervising three students, it’s been a great way to start before heading towards PGT supervision later this month. I am genuinely looking forward to supervising master’s research projects. Though I know it will be hard work, I am excited to see the innovative and ground-breaking research our students will produce. These projects allow students to delve deep into a topic of their choice, and I am honoured to guide them through this process. I plan to attend a training session with the Teaching Excellence Academy to help develop my supervision practice. I’m also looking forward to further experimenting with OneNote as a means to manage supervision.
Internationalisation of my practice
Working with international students has been an enriching and eye-opening aspect of my new position. I have gained a wealth of knowledge from their diverse perspectives and experiences, particularly concerning the different educational systems they have been exposed to. This has broadened my understanding of global educational practices and has given me the tools to incorporate these insights into my own teaching approach. As a result, I am now better equipped to support and guide students from various cultural backgrounds, enhancing the inclusivity of my teaching methods. This is, however, a long journey – and something I expect to vary as international students vary and we attract from different regions over time.
The opportunity to develop and shape the content of brand-new modules has been invigorating. Working on the third-year dissertation and research module has been great as nothing is written, giving freedom to develop something brand new. I’ve really been able to contribute to the support of literature-based dissertations and can’t wait to develop this further. Being able to draw upon my expertise and experience, I have been able to design courses that are relevant, engaging, and catered to the needs of my students. This process has been challenging and gratifying, pushing me to continuously expand my knowledge and skills. As I look forward to the year ahead, I am particularly excited to support the curriculum design process for the new master’s program. I am eager to contribute my insights and ideas to this innovative program, which promises to provide students with a comprehensive and cutting-edge education.
I have enjoyed researching contemporary topics and incorporating them into the curriculum, ensuring that our students receive an education that prepares them for the ever-evolving world of education studies. My numerous posts on Artificial Intelligence and education are good examples of such learning and experimentation. This emerging technology presents countless possibilities for enhancing teaching and learning, from adaptive learning systems to AI-driven assessment tools. I am eager to integrate it into my practice further and observe how it transforms the educational landscape.
In conclusion, my first trimester as a lecturer in Education Studies has been an incredible journey marked by growth, connection, and discovery. I am thankful for the relationships I have formed with my students and new colleagues, the personal growth I have experienced, and the opportunities that lie ahead. My increased understanding of global educational practices, the incorporation of my AI into my understanding of future learning environments, and the development of new curricula have all contributed to my growth as an educator.
As I move forward in my career, I am eager to continue expanding my horizons and making a lasting impact on the field of education. By staying current with the latest research and trends, engaging in meaningful collaborations, and fostering a genuine connection with my students, I hope to create a learning environment that empowers and inspires future educators and scholars.
Through my experiences thus far, I have developed a newfound appreciation for the immense responsibility and privilege of being a lecturer. As I continue to grow and evolve in this role, I am committed to maintaining the highest standards of professionalism, fostering a spirit of curiosity and passion in my students, and contributing to advancing the field of education studies. With anticipation and determination, I look forward to the many opportunities and challenges in my journey as an educator.
Knowles, M. S., Holton III, E. F., & Swanson, R. A. (2014) The adult learner: The definitive classic in adult education and human resource development. Routledge.
Wenger, E. (1998). Communities of practice: Learning, meaning, and identity. Cambridge University Press.
Say something profound and insightful about the impact of AI large language models in higher education in the style of a @RacePhil collaboration with @ProfSallyBrown#lthechat
Well… I couldn’t help but give it a go! I copied Simon’s tweet and used it as the prompt for GTP-4. Here is the response:
In the harmonious melding of @RacePhil’s emphasis on assessment and feedback, and @ProfSallyBrown’s dedication to transformative learning experiences, the advent of AI large language models in higher education serves as a catalyst for innovation and equity.
As digital companions, these AI models foster an environment where learning transcends traditional boundaries, enriching the educational tapestry with the threads of diverse perspectives and personalized support. Empowering students and educators alike, these models facilitate the co-creation of knowledge, nurturing critical thinking and adaptability, essential skills for the ever-evolving landscape of the 21st century.
However, we must remain vigilant in the face of potential ethical pitfalls, ensuring that the AI-driven future of higher education is built on a foundation of transparency, fairness, and inclusivity. By mindfully integrating AI into pedagogical practices, we can harness its transformative potential to augment human intellect, democratize access to quality education, and inspire a generation of lifelong learners. #lthechat
In my final experiment of the day with GTP-4, I am using the earlier AI-generated blog post, Debunking the myth of Learning Styles as the base.Peter Hartley spurred this post, acknowledging there was more fun yet to be had with GTP4 and this base material. He was right (and I promise the image at the top of this article will make sense by the end!).
Grade your earlier message that is Titled: Debunking the Learning Styles Myth: A Call for Evidence-Based Educational Practices
You are a Lecturer working at a prestigious university in the United Kingdom. You are to grade this work on a number scale from 0 to 100. A score below 40 represents a fail. You will need to provide detailed feedback to justify your grade, and you should identify areas of improvement to help your student take their work further next time.
And the grade it gave itself?
Title: Debunking the Learning Styles Myth: A Call for Evidence-Based Educational Practices Grade: 85/100
Overall, this article is well-written, presenting a coherent and compelling argument against the concept of learning styles. The language is formal and appropriate for a specialist audience, and the structure is clear and organized. The article also demonstrates a good understanding of the relevant literature.
Areas of improvement:
Depth of analysis: While the article covers the main arguments against learning styles, it would benefit from a more in-depth analysis of specific studies that debunk the concept, providing a more comprehensive critique.
Counterarguments: Addressing potential counterarguments and providing refutations can strengthen your argument. Consider discussing the reasons behind the popularity of learning styles and possible alternative explanations for the observed effects.
Practical implications: It would be beneficial to discuss specific examples of how evidence-based practices can be implemented in educational settings, giving readers a clearer understanding of the alternatives to learning styles.
Source integration: While the article cites relevant sources, it could benefit from a more seamless integration of these sources into the text. Using direct quotes or paraphrasing specific ideas from the sources can help build a more robust argument.
Originality: Although the article presents a well-established critique of learning styles, try to incorporate more original ideas or unique perspectives to make the argument more engaging and thought-provoking for your audience.
In summary, this article demonstrates strong writing skills, a clear structure, and an understanding of the relevant literature. To improve the article, focus on deepening the analysis, addressing counterarguments, discussing practical implications, integrating sources more effectively, and incorporating original ideas. Keep up the good work and continue to develop your critical thinking and writing skills.
Evaluating the feedback
Not a bad evaluation. In reality, an actual university assignment probably wouldn’t score this well in presenting only one view (unless that was the task). It is correct in that counterarguments are required.
It is also interesting to see it suggest the use of direct quotes – something we’d generally ask students to avoid in order to demonstrate their own understanding.
The nod towards originality and depth of analysis very much capture the goals required for higher-level grades.
Learning styles have been a popular topic in education for decades, with various models suggesting that individuals have different preferences for how they process and absorb information. Some of the most well-known models include Visual, Auditory, and Kinesthetic (VAK) learning styles and others like Kolb’s Experiential Learning Theory and Howard Gardner’s Theory of Multiple Intelligences.
However, the validity of learning styles as a concept has been widely debated among researchers and educators. Numerous studies have attempted to validate the existence of learning styles, but the evidence supporting their effectiveness is weak, and some even suggest that the concept is a myth. Critics argue that the idea of learning styles may oversimplify the complex process of learning and lead to ineffective teaching methods.
Instead, contemporary research points to the importance of adaptable evidence-based teaching practices that focus on learners’ diverse needs. This includes employing various teaching methods, engaging multiple senses, and addressing different skill levels rather than focusing solely on learning styles. In this way, educators can create a more inclusive and effective learning environment that benefits all students, regardless of their preferences.
The concept of learning styles has enjoyed widespread popularity in education for decades, despite a lack of empirical evidence supporting its efficacy. This post aims to challenge the legitimacy of learning styles and provide a compelling argument for why educators and researchers should be critical of their propagation. Learning styles ultimately harm learners, and the education community should embrace evidence-based practices instead.
1 – Lack of Empirical Evidence for learning styles
A cornerstone of any effective educational theory is a robust body of empirical evidence. However, numerous studies have failed to provide conclusive support for the existence of learning styles or their impact on learning outcomes (Coffield et al., 2004; Pashler et al., 2008; Willingham et al., 2015). Meta-analyses have revealed a consistent lack of empirical evidence to validate learning styles (Coffield et al., 2004; Pashler et al., 2008), indicating that the concept is built on shaky foundations.
2 – Oversimplification of Learning
The idea of learning styles oversimplifies the complex and multifaceted process of learning (Geake, 2008; Hattie, 2009). Learning is not solely determined by individual preferences but is influenced by a myriad of factors, including prior knowledge, cognitive abilities, motivation, and socio-cultural context. By reducing learning to a set of static styles, educators may inadvertently neglect these crucial aspects of the learning process, hindering their ability to cater to students’ diverse needs (Dunn & Griggs, 2000).
3 – Perpetuation of Stereotypes
The propagation of learning styles may reinforce stereotypes and an overly deterministic view of learners (Scott, 2010). By labelling students as “visual,” “auditory,” or “kinesthetic” learners, educators may inadvertently constrain students to a particular mode of learning, limiting their potential for growth and development (Dweck, 2006). This typecasting may contribute to self-fulfilling prophecies and hinder students from exploring alternative learning strategies, ultimately hindering their academic progress (Dweck, 2006).
4 – Misallocation of Resources
The continued acceptance of learning styles may misallocate educational institutions’ resources (Paschler et al., 2008). Schools and districts divert valuable resources away from evidence-based practices by investing time and money in training teachers and developing learning materials based on a concept with weak empirical support (Hattie, 2009). This misallocation has significant implications for the quality of education and students’ academic success.
5 – The Opportunity Cost of Ignoring Evidence-Based Practices
By propagating learning styles, the education community risks neglecting evidence-based practices that have been shown to improve learning outcomes (Hattie, 2009). These practices include formative assessment, feedback, metacognitive strategies, and collaborative learning (Hattie, 2009; Zimmerman, 2002). By focusing on debunked theories such as learning styles, educators may miss opportunities to implement strategies that genuinely improve student learning.
The persistence of learning styles in educational discourse is a concerning phenomenon that warrants critical examination. Given the lack of empirical evidence and the potential harm caused by the propagation of learning styles, we urge educators and researchers to abandon this outdated concept and embrace evidence-based practices. Doing so can create a more inclusive, effective, and empirically grounded educational environment that benefits all learners.
Coffield, F., Moseley, D., Hall, E., & Ecclestone, K. (2004). Learning styles and pedagogy in post-16 learning: A systematic and critical review. Learning and Skills Research Centre.
Dunn, R., & Griggs, S. A. (2000). Practical approaches to using learning styles in higher education. Greenwood Publishing Group.
Dweck, C. S. (2006). Mindset: The new psychology of success. Random House.
Geake, J. (2008). Neuromythologies in education. Educational Research, 50(2), 123-133.
Hattie, J. (2009). Visible learning: A synthesis of over 800 meta-analyses relating to achievement. Routledge.
Pashler, H., McDaniel, M., Rohrer, D., & Bjork, R. (2008). Learning styles: Concepts and evidence. Psychological Science in the Public Interest, 9(3), 105-119.
Scott, C. (2010). The enduring appeal of “learning styles.” Australian Journal of Education, 54(1), 5-17.
Willingham, D. T., Hughes, E. M., & Dobolyi, D. G. (2015). The scientific status of learning styles theories. Teaching of Psychology, 42(3), 266-271.
Zimmerman, B. J. (2002). Becoming a self-regulated learner: An overview. Theory into Practice, 41(2), 64-70.
This blog post discusses the possibility of the IKEA LEGO sets for LEGO Serious Play. In 2018, IKEA and LEGO announced they were going to play together. This led to the development of the BYGGLEK LEGO collection, available exclusively at IKEA stores. This product range included a series of LEGO storage boxes and a set of 201 LEGO bricks designed for free play. As described by IKEA:
Creating more space for play The BYGGLEK LEGO® collection offers play storage solutions and a LEGO brick set unique to IKEA. The boxes easily find harmony with your home so the creations can be put on display, keeping the story alive until the next play time.
Having used LEGO Serious Play as an aspect of my research and work for some years, I’ve recently considered how the BYGGLEK LEGO collection can be used for LEGO Serious Play. Before I get into this, however, a brief introduction to LEGO Serious Play:
What is LEGO Serious Play?
If you’ve not used LEGO Serious Play before, it is a creative approach to meeting facilitation that uses LEGO bricks as a form of collaboration and communication. It has a track record of success across education and business – shaking up traditional meetings and learning opportunities with the use of LEGO. This has taken it beyond meetings and into the classroom and sphere of research.
Think about all the times you’ve set out Flipchart and pens – and most groups struggle to settle on a scribe – ‘You do it’ – ‘No! You!’. This doesn’t happen with LEGO Serious Play. Everyone is in! I’ve used LEGO Serious Play with participants of all ages for research, learning and business strategy purposes.
IKEA and LEGO Serious Play
So far, my LEGO Serious Play practice has focused on a large collection of bricks that all participants share. I blogged about the sets used to build my LEGO Serious Play collection, and since 2021, that collection has been the staple of my LEGO Serious Play kit. I’ve recently wanted to explore individual LEGO Serious Play kits so each participant has their own bricks. This can reduce the scrabble for bricks between participants and reduce much of the noise in the session (something some participants can find distracting).
There is also a potential for equity. One of the LEGO Serious Play practitioners I worked with insisted on participants having the same bricks. This raises the question – what bricks to use? My colleague went to a LEGO Store and used the Pick a Brick wall to build a collection of identical sets. This has always been too risky for my liking – too reliant on the store’s stock of bricks. It’s also a bit of an administrative hassle, especially if the store is busy. Then came the BYGGLEK LEGO Set:
Digging into the BYGGLEK set
This IKEA-exclusive LEGO set contains 201 bricks, including a brick remover. Within the set there are a range of plates, bricks, a door, some windows, a range of small bricks and enough parts for two Minifigures. As I’ve come to get to know this set in closer detail, I’ve become more convinced it’s a perfect range for LEGO Serious Play. It has a really nice range of bricks, allowing participants to communicate a whole range of ideas. So you can get an idea, I’ve laid out the bricks in this box below:
At 201 bricks, it feels a really nice size for individual use. I love the variety of bricks included in the set. There is a handful of regular bricks, but the body of the set includes a variety of brick colours and sizes. It has some nice, intricate details. I love the inclusion of some leaves and green elements alongside some food pieces, windows and a door.
Just the right size and configuration
This catalogue image gives you a good idea of the scale of the set – or the scale of the models that can be built with it. It isn’t enough LEGO to make the larger, more dramatic models – but it’s good enough for some detailed and intricate models (which is my favourite kind – every brick has meaning. The two Minifigures are nice and echo the days of plainer characters, a contrast to a lot of the licensed figures that dominate now.
While there is debate over using Minifigures for LEGO Serious Play, I’ve always included them in my sets. Yes – it can funnel participant responses around more concrete than the metaphorical use of LEGO, it can also enable the metaphorical messages. I’ve had too many participants wasting time building something to represent people or a person. Minifigures just cut straight to it! As mentioned above, the plainness of these figures also stops the message from getting conflated with a licensed character.
Keeping things tidy – the BYGGLEK Storage boxes
IKEA brought their famed trend to the BYGGLEK collection – flat-pack LEGO! Yes! They’ve managed to create flat-pack LEGO in a way only IKEA could. The BYGGLEK collection includes four different sizes of LEGO storage box. The two smaller sizes are fully assembled and come in a box of three (one small box, two extra small boxes). The two larger size boxes are the ones requiring assembly. It’s a tool-less construction, and the pieces click well together to create a solid box, perfect for storing LEGO. More importantly, the box lids double as LEGO base plates. The boxes themselves can also be used as part of the build, and the larger boxes have LEGO-compatible recesses.
So – back to LEGO Serious Play! The medium-size BYGGLEK box (26x18x12 cm) is great for storing those individual LEGO Serious Play kits. The BYGGLEK LEGO set fits within the box nicely and includes some nice LEGO-compatible studs that can be used in models. There is also enough space for digging through the pile of bricks to find what you need – within the box. The box itself can also be used as part of the models, of course. Unfortunately, the lid sits on top of the box – it doesn’t click securely. As such, I tend to use elastic bands to hold things together when I’m on the move. Not a great look – but it does the job.
Over to you!
I hope this post has been useful! Let me know what you think. I’d also love to hear if anyone else has used the IKEA + LEGO combination for LEGO Serious Play ????
This post lists the leading Generative AI tools that produce outputs based on natural language text prompts. This page is inspired by @aaronsiim’s Generative AI list, but focuses on the text-based tools and provides accessible links to them.
These tools turn text into audio using AI to produce more human-like speech, including tone and inflexion.
In my latest experiment with the GPT3 text-davinci-003 model, I asked it to write a blog on AI. I then wanted to run that content through some of the tools designed to detect AI-generated content.
Step 1: Adjusting the AI model’s settings
Temperature: 1 (This controls randomness. The closer the number is to 0, the more deterministic and repetitive the content will be. I wanted this as far away from 0 as it would accept.
Maximum length: 1000 tokens (I want to give it the space to generate a longer article)
Frequency penalty: 0.5 (Decreases likelihood of a repeated line)
Presence penalty: 0.5 (Increases likelihood of talking about new topics)
Best of: 3 (This will run the completion three times server side and display the best)
Step 2: Prompts for the AI
To produce the blog article, I sent the following prompts:
Write a high quality, but witty and amusing blog post that explains the benefits of artificial intelligence in the context of university-level education
The above copy is great. But nowhere near long enough. Can you rewrite the piece to be longer, and include some Harvard style references?
That's almost perfect. Can you make it even longer and funnier - in a dry humor kind of way.
Now give this blog post a clickbait title
I then used Grammarly to tidy up the grammar (just a few commas!).
Step 3: The final result – AI output:
Discover the Surprising Benefits of AI in University-Level Education!
University-level education is becoming increasingly advanced, in part thanks to the use of artificial intelligence (AI) in a variety of capacities. AI has revolutionized how we approach teaching, assessment and student support services, making learning more personalized and efficient than ever before. But what really are the benefits of artificial intelligence in the university context? Well, let me explain…
To begin with, AI technology can be used to assess student work quickly and accurately by offering automatic marking tools that give instant feedback on assignments (Lee & Voyer, 2019). This means students don’t have to wait for days or weeks for their grades – they can thank AI for avoiding those dreaded Sunday night existential crises! Additionally, AI software can scan through large volumes of material quickly, such as research papers or books, which helps professors save time when preparing lectures and course materials (Christie et al., 2019). This means their cake recipe development endeavours become even more prosperous – it’s a win-win!
Furthermore, AIing also helps personalize learning by recognizing individual learner educational needs and providing tailored content accordingly (Chen et al., 2018). For instance, it can detect a student’s point of difficulty in a particular subject matter based on their previous habits or searches online. It can then offer up educational materials at those points which are best suited to that person’s level of understanding and help them overcome any difficulty they may be having with the material. The best part? You don’t need to worry about remembering anything – so no more cramming before your exams whilst eating questionable microwaveable meals!
Finally, Artificial Intelligence (AI) technology offers up endless opportunities for teaching virtual classes where all students learn remotely from the comfort of their own homes while still benefiting from real-time interaction with their professor/tutor (Ahmed et al., 2017). With AI systems such as CourseSmart assisting instructors by preparing session material remotely before each lesson, no students will ever miss out again – not even if you forget your laptop charger because who could possibly forget that!?
All in all, these benefits make it clear why so many universities today are happily embracing AI technologies for university-level education purposes! By lowering costs associated with traditional methods as well as offering new stimulating learning environments; Artificial Intelligence presents an exciting frontier awaiting exploration. So why not get started today? Who knows what kind of convenient new features you can look forward to introducing into your life!?
Ahmed I., Ullah K. A., Khan S., & Abbas M. (2017). Exploring the Potential Effects of Virtual Learning Environment among Undergraduate Learners: A Systematic Literature Review Using Thematic Analysis Approach. Computers & Education Journal. 112:204-222.
Chen C.-S., Chen T.-H., Chiu H.-Y., & Tsai C.-C.(2018). Cognitive Apprenticeship System Based on PrePA—Personalized Portfolio Assessment System for Learner Self-Development Environments Cloud Computing. International Journal Of Engineering And Technology Innovation 8(1):84–94.
Christie T., Wright C., Matthaei J ., Mureithi P .& Hobbs V .(2019). OERHub Final Report – Compendium Of Tools And Resources For Open Educational Resources Practitioner Support In Higher Education Institutions Around The World: Progress Report, Version 1 Harvard Graduate School Of Education
Lee S.-K& Voyer v.(2019). Soft Computing In Education: New Trends And Approaches: Learning Through Technology For All | Qsearch Ltd
NOTE: All of those references are garbage. Those sources don’t exist – though it looks convincing…
Testing the above article: Was it written by AI?
Well – we know the answer. It was, indeed, written by an AI. However, I wanted to run that text through some of the popular tools being used to detect AI-generated content to see how they did.
I can see why. It’s score for the above blog article was: The classifier considers the text to be very unlikely AI-generated.
GPTZero works by measuring the text’s perplexity and randomness. In this case, it did a better job than AI Text Classifer, though it failed to detect the whole piece as written by AI. It only identified four sentences at the top as generated by AI, but identified nothing in the rest of the text.
GPT-2 Output Detector Demo
In fairness, this was designed for GPT-2, and the model used for the above article was substantially enhanced. Unsurprisingly, GPT-2 Output Detector scored the piece as real:
Next, I tried Writer AI Content Detector. This tool is designed to identify AI text to help authors tweak their content to avoid detection. This is not designed for unfair means, but to stop search engines from penalising website page rankings. Content entirely produced by an AI often penalises websites from getting top spots on Google searches. Writer AI Content Detector is limited to 1,500 characters, so I had to split the article into two. Both halves were scored 100% for human-generated content…
Giant Language model Test Room (GLTR)
GLTR (glitter) “enables forensic inspection of the visual footprint of a language model on input text to detect whether a text could be real or fake”. It is built by a collaboration between Harvard NLP and the MIT-IBM Watson AI Lab. Similar to the GPT-2 Output Detector Demo, it was designed for GPT-2. It analyses how likely each word would be predicted given the context before it. It is pretty cool, as you can see word-by-word likelihood predictions for the next word:
Words highlighted in green are in the top 10 for most likely. Yellow words are in the top 100, and red words the top 1,000. A violet word is even more unlikely to be detected. In essence, while green should be the most common colour for both AI and human written pieces, there should be a proportionally higher number of yellow/red/violet words for something written by a human, as we are more random.
In this case, I was really shocked by the output. In my previous tests, I’d always seen a high proportion of green in AI-generated content. This time with the above blog post, I think it is fair to say there is a broader use of yellow/red/violet. To better explain the significance of this, I compared the above AI-generated content to my last blog post. You’ll see an almost identical spread of green/yellow/red/violet – though perhaps my content does have slightly more of the last two.
I hadn’t expected that. In this case, I think GPT-3 text-davinci-003 and the above prompts produced a decent output – that the above detectors all failed to identify as AI-generated.
I think it’s important to consider human detection. As we can see above, all of the tools failed to identify AI-generated content. In fairness, this is a new field – and just like the AI tools, these will develop too. In this case, human detection certainly wins. As you can see from the article, it has made up a load of references. They look convincing – and those journals, volumes and issues exist. The articles, however, do not.
Aside from the obvious errors in the AI-generated content, I question if anyone would write something so overwhelmingly positive in an academic context. Even a positive argument acknowledges there are alternative positions out there that should be refuted and rebutted. Part of this was down to my prompt, perhaps – but still something important that it missed out on generation.
I do think it did the funny, witty part well. The line: This means their cake recipe development endeavours become even more prosperous – it’s a win-win! was highly unlikely to be written by an AI in the above model.
Conclusion: AI-generators can trick AI-detectors
As you can see, there is still a long way to go in developing GPT-3 detection – which is perhaps concerning given that GPT-4 is on the way. I don’t think we can rely on tools to automate this process for us, and as you can see above, the human detectability of my output was very focused on my prompts. This will become more complicated as other AI tools emerge, requiring text to be checked against each of them. Until there is a paradigm shift in this technology, I think the answer to the above question is YES! An AI generation tool can certainly trick an AI detection tool.
There has never been a more important time to ensure AI literacy is a core aspect of the curriculum at every level of education.
It’s an honest question. Everywhere I look, there are discussion threads, social media posts and emails from Higher Education professionals obsessing over artificial intelligence. Most of these communications focus on ChatGPT, but some acknowledge other tools exist. These ‘new developments’ in artificial intelligence have prompted a dramatic response from the education sector. It has been described as a crisis, a moral panic, an ‘end to homework‘ and a threat to higher education. I think my favourite contribution this year comes from The Mail, which announces artificial intelligence could make ‘mankind extinct’.
Okay. Some perspective is needed. But my real question is this: How did the Higher Education (HE) sector not see this coming?
Artificial Intelligence has powered your work for years
In the UK, the vast majority of Universities use Microsoft (Office) 365 and the Windows operating system. Microsoft’s Outlook powers our emails, SharePoint/OneDrive stores our files, Teams manages our collaboration, and Office keeps us productive. Since 2016, Microsoft’s ‘Office Intelligent Services‘ have seamlessly integrated artificial intelligence-powered features into our everyday working lives. For most HE practitioners, the developments in artificial intelligence have been staring us in the face. Literally. The documents we write, the slides we develop, the emails we read, and the Teams calls we make have all been enhanced by Artificial Intelligence for YEARS.
Artificial intelligence in Microsoft (Office) 365:
Read aloud has turned text-to-speech, enhanced to use tone and inflexion.
Dictate has enabled speech-to-text, allowing people to talk instead of type. This includes
Optical Character Recognition has helped turn image-based text into readable characters.
Presenter Coach has analyzed people’s speech, language and body language to deliver real-time presentation feedback in PowerPoint.
Slide Designer has taken draft slides and automatically added design elements and images to make slides more effective.
Accessibility Checker has allowed the automatic generation of ALT text for images, using computer vision.
MicrosoftViva has provided detailed insights: reading your emails to identify unfinished tasks and checking your calendar to provide useful documents for meetings – in real-time.
Subtitles and Transcription have enabled PowerPoint and Teams to provide real-time subtitles for presentations, calls and recordings.
Excel has offered enhanced chart types (i.e. Maps) and real-time, streamed data (i.e. Stocks).
Editor has offered enhanced spelling and grammar advice, and has extended to use text prediction to save time when writing.
Translate has offered real-time translation from text, images and speech across up to 100 languages (and variants).
Scheduler has coordinated meetings between people – and even booked rooms.
Natural language queries in Excel have allowed people to use questions, not formulas.
Search enhanced with AI when using Bing.com
The examples above are just workplace, education and consumer applications. In industry, Microsoft-powered AI has been detecting facing, monitoring crops, enhancing video games, fighting fraud and detecting faults across hundreds of sectors. I can understand people not being aware of some of these applications – but the stuff listed above has been right in front of our eyes.
How can any of these artificial intelligence developments be a surprise?
So. Reflecting on the list above, ‘Intelligent Services’ have supported reading and writing across the Microsoft (Office) 365 platform for over eight years(!!!). If you’ve been using Microsoft Office productivity applications like Outlook, Word and PowerPoint – I cannot understand how ChatGPT can be a surprise. Office applications have started:
correcting your writing and predicting what you will say
reading your emails to manage your diary and tasks,
listening to you, so you don’t need to write,
automatically making things accessible with subtitling and computer vision
The list goes on. If artificial intelligence has been doing all this for years – how is ChatGPT such a leap?
I can understand how ChatGPT feels like a significant step up from previous chatbots. But I don’t see how it can be all that surprising when we reflect on those daily developments and how artificial intelligence has slowly become part of the everyday. It isn’t just at work or in education. Your last test at the hospital might have been screened by artificial intelligence. Every time you make a purchase, the transactions are scrutinised by artificial intelligence for anomalies. It really is everywhere. I get how the quality of written response is shocking – but given what we’ve seen happen in Microsoft (Office) 365 over the last few years – I don’t think we can call it a surprise.
Why the last-minute response?
I honestly do not know the answer to this question. The radical potential of artificial intelligence has been staring everyone in the face for years. Every email. Every document. Every Teams call. Every PowerPoint. Artificial intelligence has been prompting, pushing, helping and enhancing for years. How can ChatGPT be such a surprise? I am absolutely shocked that schools, colleges, and universities are so late in reacting to the challenge artificial intelligence poses to traditional assessment. This should not be a surprise. Not at all. I cannot understand how future scanning and business planning did not identify this as part of long-term strategies. Emergency planning and task groups should not be necessary! Educational policies should have been prepared years ago.
But they weren’t.
As such, the kneejerk reaction has been to ban artificial intelligence in many educational establishments. Given the circumstances – this is probably the right answer. For now. In future, I urge educational leaders to reconsider artificial intelligence and look at how it can be used alongside the curriculum.
Artificial intelligence in the curriculum
Our students will be leaving the educational world to join workplaces that use artificial intelligence. It might not even be labelled as such – but it will be there in the background. The example of Microsoft (Office) 365 in this very post is a great example of this in application. As such, we need to equip our students for this. Not just the practicalities of using artificial intelligence – but the difficult questions around ethics and responsibility of use too. These skills cannot be developed under a ban.
Artificial intelligence reproduces the biases of society. Our students must be equipped to challenge this.
Artificial intelligence uses Machine Learning – but this is often targeted at a range of information- including high-quality, questionable and poor-quality sources. Students need to be able to identify fact from fiction.
Artificial intelligence supports accessibility, it can translate, see and write for anyone who needs support with it. While not perfect, those features cannot be turned off.
The last word – The future of Higher Education with ChatGPT
I couldn’t help but close this post by handing over the conclusion to ChatGPT. I asked it to tell me the best-case scenario for the inclusion of artificial intelligence in university education.
The best-case scenario
In the best-case scenario, artificial intelligence (AI) will have a positive impact on university education. AI will help to improve the quality and efficiency of education by providing students with personalized learning experiences. AI-driven tutoring systems will be able to analyze a student’s performance and give immediate feedback and recommendations for improvement. AI can also be used to create adaptive learning systems that adjust the difficulty of tasks based on a student’s progress, allowing students to move at their own pace and make the most of their learning experience.
AI can also be used to automate administrative tasks, such as grading, making it easier for professors to focus on teaching and providing students with the best possible learning experience. AI-enabled analytics can be used to identify students at risk of dropping out, so appropriate interventions can be put in place to increase their chances of success. Finally, AI can be used to offer more engaging learning experiences, such as interactive simulations and augmented reality. All of this will enable universities to provide a higher quality of education while reducing costs and increasing student satisfaction.
(ChatGPT, 2023 – Published by OpenAI)
…and the worst-case scenario?
In the worst-case scenario, artificial intelligence (AI) could have a detrimental impact on university education. AI-driven tutoring systems could be overly rigid, unable to adapt to individual students’ needs, and lead to a one-size-fits-all approach to learning. AI-enabled analytics could be used to track student progress and create an environment of surveillance and control, where students feel that their every move is being monitored and judged. In addition, AI-driven automation of administrative tasks could lead to job losses, as universities reduce their staff numbers in favor of automated systems. This could lead to a decrease in the quality of education, as universities focus on cutting costs rather than on providing students with the best possible learning experience. Finally, AI-enabled simulations and augmented reality could lead to a decrease in critical thinking and problem-solving skills, as students become reliant on pre-programmed systems. All of this could lead to a decrease in student satisfaction and an overall decline in the quality of university education.
(ChatGPT, 2023 – Published by OpenAI)
Okay – I had a bit of fun with the conclusion. But ChatGPT makes a valid point… there is a lot of potential disruption – good or bad – coming to HE. The question still remains:
How did most HE practitioners not see this coming?