Yesterday I used STORM to create a short article that tried to answer the question, “What is the most likely impact of generative AI on the higher education system, taken to it’s logical end-point?” In that post I noted my disappointment with the report that STORM created and wanted to try and find a more strongly opinionated response.
So today I took the PDF output that STORM produced in response to the question above, and gave it to Claude with the following prompt:
I’ve uploaded something that I think of as a very conservative, palatable, answer to the question: “What is the most likely impact of generative AI on the higher education system, taken to it’s logical end-point?” In my opinion, this article takes today’s version of generative AI, and explores how the higher education sector might respond. What it doesn’t do, is actually answer the question, which includes the qualifier: “taken to it’s logical end-point”. I don’t want to see how the higher education sector should respond to today’s generative AI models. I want to extrapolate the trend of generative AI through the next 2 generations, and ask what impact those models will have. Can you take these issues I have, and let me know what you think of the attachment?
Claude gave me a response that I thought was pretty reasonable, but I wanted to push it further, so I followed it up with:
I think your timelines for the next 2 generations of generative AI are too conservative, but that’s not too much of an issue. Whether we get to that point in 5, 10, or 20 years doesn’t really matter. What I’m looking for is the impact of these advanced capabilities on traditional systems of education, like universities. I like your initial response. However, I’d like you to have another go, thinking step-by-step about how significantly advanced AI is likely to impact the higher education system.
I appreciated Claude’s explanation for it’s second response, making it clear that this is a ‘radical approach’, which is what I was looking for:
This comprehensive analysis takes a more radical approach to examining the potential impacts of advanced AI on higher education. It considers how AI could fundamentally reshape the nature of knowledge, learning, and the role of educational institutions. Here are some key points to consider:
- The analysis assumes AI capabilities that far exceed current models, potentially approaching or achieving artificial general intelligence (AGI).
- It explores scenarios where traditional educational structures become obsolete, replaced by AI-driven, personalized, and continuous learning models.
- The role of universities is reimagined, shifting from knowledge providers to facilitators of human-AI collaboration and centers for developing uniquely human skills.
- The analysis considers the broader societal and economic implications of these changes, including the potential democratization of elite education and the need for lifelong learning in a rapidly changing job market.
- Ethical challenges are highlighted, particularly concerning educational equity and the appropriate boundaries between human and AI roles in education.
This approach aims to push the boundaries of how we think about the future of higher education in a world where AI capabilities have advanced significantly. It presents a more transformative vision compared to the original document, which focused more on how current institutions might adapt to near-term AI developments.
For what it’s worth, the description below is reasonably well-aligned with where I think we’re heading, and I recognise that this diverges a lot from the standard narrative. To state the obvious, this is the direction I was pushing Claude in, so it’s not surprising to see these suggested outcomes. You could push in another direction and get different outcomes.
Side note: When I gave the final version of this post to Claude and asked for comment, it suggested that it was too radical and that I should aim for something more balanced. I didn’t do that, because a radical vision is what I was going for. But even Claude was trying to bring me back towards the centre.
Assuming the current trend continues (and I realise that’s a very big assumption…but also, not an obviously wrong assumption), I can’t see why we don’t get to some version of what’s described below. And if there’s even a small chance that we’re heading in this direction, what do we lose by starting to prepare for it now?
Note my annotations and comments in italics in the list below.
Comprehensive analysis of advanced AI’s impact on higher education
Redefining the nature of knowledge and expertise
AI as omniscient knowledge repository
- AI systems become the primary source of all human knowledge, constantly updated in real-time.
- Traditional academic expertise becomes less valuable as AI can provide more comprehensive and up-to-date information.
Shift in value of human knowledge
- Memorization of facts becomes obsolete.
- Premium placed on uniquely human abilities: creativity, emotional intelligence, ethical reasoning, and interdisciplinary synthesis.
- For what it’s worth, I don’t think that this is where we carve out our niche; AI is already very good at creativity, emotional intelligence, ethical reasoning, and interdisciplinary synthesis i.e. these are not uniquely human skills.
Transformation of learning processes
Hyper-personalized learning paths
- AI creates fully customized curricula for each student, adapting in real-time to their progress, interests, and goals.
- Traditional course structures and degree programs become obsolete.
Immersive learning environments
- AI-powered virtual and augmented reality creates highly engaging, interactive learning experiences.
- Physical campuses may become unnecessary for most educational purposes.
Continuous, lifelong learning model
- Education shifts from a fixed-term endeavor to a constant, ongoing process.
- Traditional concepts of “graduation” and “alumni” lose meaning.
Redefinition of educational institutions
Decentralization of education
- Universities as centralized knowledge hubs become obsolete.
- Emergence of distributed learning networks facilitated by AI.
Shift in institutional value proposition
- Universities transition from knowledge providers to curators of learning experiences and facilitators of human connections.
- Focus on developing critical thinking, creativity, and ethical reasoning skills that complement AI capabilities.
- See my point above re. these not being uniquely human skills.
Democratization of elite education
- AI replicates and scales the best educational experiences, making them universally accessible.
- Traditional university prestige may diminish in importance.
Evolution of assessment and credentialing
Continuous, real-time assessment
- Traditional exams and grading systems become obsolete.
- AI provides constant feedback and evaluation of skills and knowledge application.
Competency-based credentialing
- Shift from degree-based to skill-based credentialing.
- Emergence of dynamic, AI-verified portfolios of competencies.
Redefining academic integrity
- Traditional concepts of plagiarism and cheating become irrelevant.
- Focus shifts to evaluating how effectively individuals can collaborate with AI to solve problems.
Transformation of research and innovation
AI-driven research
- AI systems capable of generating hypotheses, designing experiments, and interpreting results.
- Human researchers focus on asking novel questions and providing ethical oversight.
- Some evidence that genAI systems ask more novel questions. And I’m not sure that we’re best positioned to supply the ethical oversight either.
Accelerated innovation cycles
- AI dramatically speeds up the process of discovery and innovation.
- Universities may struggle to keep pace with the rate of knowledge advancement.
- It won’t be universities running AI-based research projects; it’ll be startups, established companies, and probably people working from home.
Redefinition of faculty roles
Shift from knowledge transmission to facilitation
- Traditional lecturing becomes obsolete.
- Faculty focus on guiding students in critical thinking, ethical reasoning, and creative problem-solving.
- Again, I’m not sure why the assumption is that we’re going to be the best guides for these skills.
- And worse than that, if AI is better at these things than we are, then why would we be teaching students these skills at all?
AI-human collaborative teaching
- Faculty work alongside AI systems to design and facilitate learning experiences.
- Emergence of new roles focused on AI-human educational integration.
Economic and workforce implications
Rapid skill obsolescence
- Constant need for reskilling and upskilling.
- Universities may transition to providing continuous, modular education throughout individuals’ careers.
- See, for example, the 60-year curriculum.
Shift in employer expectations
- Less emphasis on traditional degrees, more on demonstrated skills and ability to work with AI.
- Universities may need to radically redesign their offerings to remain relevant to the job market.
- Not just redesign their offerings, but how they are structured.
- In fact, after the kind of restructuring I think would be necessary, would they even be recognisable as universities?
Ethical and societal challenges
AI bias and educational equity
- Need for robust systems to ensure AI doesn’t perpetuate or exacerbate existing inequalities in education.
- Mmm…why are there no concerns about existing systems that perpetuate and exacerbate inequality?
- Universities may take on new roles in auditing and ensuring the fairness of AI-driven education.
- Here’s another option: AI takes on the role of auditing and ensuring the fairness of human-informed education.
Human-AI boundaries in learning
- Ethical debates about the appropriate role of AI in education and knowledge creation.
- Universities become centers for discussing and shaping the future of human-AI interaction in learning and research.
- I’m not sure why universities have to be the location for this kind of work. I imagine this could be done by networks of people anywhere in the world.
Conclusion
The impact of advanced AI on higher education is likely to be transformative and disruptive. Traditional universities will need to radically reimagine their role, structure, and value proposition to remain relevant. The focus of education will shift from knowledge transmission to developing uniquely human capabilities that complement AI. This transformation will require a fundamental rethinking of what education means and how it is delivered in an AI-driven world.