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.
- Microsoft Viva 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.
It was some relief to see ‘This shouldn’t be a surprise‘ published while I write this post!
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.
It’s fair to say – the news isn’t all doom and gloom. It’s been nice to see some new articles discussing how artificial intelligence won’t hinder creativity, will help schools teach skills for university and how it can be integrated into teaching. It is also interesting to see reflections on the OpenAI website (ChatGPT’s creator) about how it can support streamlined and personalised teaching – amongst many opportunities and threats.
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.(ChatGPT, 2023 – Published by OpenAI)
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.
…and the worst-case scenario?
(ChatGPT, 2023 – Published by OpenAI)
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.
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?
Answers in the comments ?