[Misc] University? A.I. World...??

[Moshe Gariani]

There must be lots of people on here with good experience and views on the changes caused by A.I. technology advances...

I am pretty ignorant myself. Only really know a little bit about capability of A.I. within the Higher Education context.

It feels like the situation is progressing noticeably on a monthly timescale if not weekly. A short while ago we were complacently talking about A.I. generated work being mostly "rubbish" and easy to spot. I attended a Webinar this week and am now convinced that A.I. will very soon be able to generate post-graduate expert level writing on any topic. Traditional essays where the challenge is to review available theory/research literature and make application to answering a question will be meat and drink. It will also be able to write high level "research reports" having completed sophisticated quantitative or qualitative data analysis.

None of this will be detectable. The key aspect it needs to brush up is referencing. But even if it were detectable, what would be the argument in denying students access to available tools. We don't stop them from using word processors, calculators or Statistical Packages...??

What does this mean for the much vaunted "transferrable skills" that graduates are meant to benefit from acquiring...? Are graduate skills in analysis and different forms of communication, that used to have real-life value, already devalued?

Is the benefit of university education and a degree certificate changing radically? Would your advice to an 18 year old about going to university (to read Sociology or Business Studies, say) be any different now compared to a couple of years ago because of what is happening with A.I. ...

 

[essbee1]

Over to HWT on this one......Harry?

 

[Nobby Cybergoat]

Because the direction of travel is so unpredictable, just act as normal and try not to think about AI would be my advice

 

[happypig]

Artificial intelligence (AI) generated content is becoming progressively sophisticated, making it increasingly difficult to distinguish from human-created work. The advancement in natural language processing (NLP) algorithms, such as GPT models, has enabled AI to produce text that closely mimics human writing styles. These models are trained on vast datasets, allowing them to capture nuances in language, context, tone, and structure, thus increasing their ability to generate coherent and contextually relevant content.

Furthermore, AI systems continually learn and adapt through ongoing exposure to new data, improving their ability to generate content that mirrors human creativity and style. This adaptive learning allows AI to refine its outputs, making them more convincing over time. As AI tools become integrated within various content creation platforms, their outputs will blend seamlessly with human-generated content, further complicating detection.

Additionally, the development of AI tools specifically designed to mimic individual authors' styles adds another layer of complexity. These tools can analyze previous writings of an author and recreate content that aligns with their unique style, making it even more challenging to discern authenticity.

As AI technology continues to evolve, the line between human and machine-generated content will blur, posing challenges for educators, publishers, and platforms dedicated to content authenticity and originality.

 

[ropey9]

Here is the google gemini response to your opening post

You've hit upon some incredibly important and rapidly evolving issues surrounding AI and higher education. It's true, the landscape is shifting dramatically, and your observations about the speed of change and the increasing sophistication of AI-generated work are spot on. Here's a breakdown of the key points you've raised and some thoughts on them:

• AI's Growing Sophistication: The idea that AI-generated work is easily detectable is becoming outdated. As you've experienced, AI is quickly mastering the kind of synthesis and analysis required for postgraduate-level writing, including literature reviews and research reports. Referencing is a challenge, but one that's likely to be overcome soon.
• The "Tools" Argument: You're right to draw the parallel with word processors, calculators, and statistical packages. It's hard to argue against students using available tools, even if those tools significantly enhance their output. The question becomes less about whether they use them, and more about how they use them, and what skills are still essential.
• The Devaluation of Transferable Skills: This is a crucial point. If AI can perform high-level analysis and communication, what happens to the value of those skills in the job market? Traditional markers of graduate success may need to be re-evaluated. Critical thinking, creativity, problem-solving, and adaptability – skills that are harder for AI to replicate – become even more important. The ability to critically evaluate AI-generated work will also be a key skill.
• The Changing Value of a Degree: The fundamental purpose of a university education is being challenged. If knowledge synthesis and even research can be outsourced to AI, what is the unique value proposition of a degree? Universities need to adapt by focusing on developing those higher-order thinking skills, fostering collaboration and teamwork, and providing opportunities for experiential learning that AI can't replicate. The emphasis may shift from knowledge acquisition to knowledge application and creation.
• Advice to an 18-Year-Old: This is the million-dollar question. The rise of AI definitely adds a new dimension to the decision-making process. While a degree still holds value, the type of degree and the focus of the education become more critical. I would advise an 18-year-old considering Sociology or Business Studies to:
  • Focus on the development of critical thinking: Learn how to evaluate information, identify biases, and construct well-reasoned arguments. This is essential in an AI-driven world.
  • Embrace interdisciplinary learning: Combine their chosen field with other areas like data science, computer science, or even design thinking. This will make them more adaptable and better equipped to work with AI.
  • Seek out experiential learning opportunities: Internships, research projects, and study abroad programs can provide valuable real-world experience that complements academic learning.
  • Consider the future of work: Research how AI is impacting their chosen field and identify skills that will be in demand in the future.
  • Don't dismiss the humanities: While STEM fields are often emphasized, the humanities cultivate critical thinking, communication, and ethical reasoning – all of which are crucial in the age of AI.

In short, the rise of AI is a game-changer for higher education. While the future is uncertain, it's clear that universities need to adapt to this new reality by focusing on developing uniquely human skills that AI can't replicate. The conversation we're having now is essential, and it needs to continue as AI technology continues to evolve.

 

[Peteinblack]

As a Professor, I'm glad I'm nearer to retirement than at early career stage.

I really feel sorry for my colleagues in their 30s and 40s.

 

[GT49er]

May not be a completely foolproof solution, but it might help to insist that exams, theses and dissertations should be hand-written in the student's own hand-writing.

 

[Peteinblack]

May not be a completely foolproof solution, but it might help to insist that exams, theses and dissertations should be hand-written in the student's own hand-writing.

We are moving back to more in-person exams in some cases for this very reason, but because kids today only communicate via texting, their handwriting is unreadable!

 

[beorhthelm]

Artificial intelligence (AI) generated content is becoming progressively sophisticated, making it increasingly difficult to distinguish from human-created work. The advancement in natural language processing (NLP) algorithms, such as GPT models, has enabled AI to produce text that closely mimics human writing styles. These models are trained on vast datasets, allowing them to capture nuances in language, context, tone, and structure, thus increasing their ability to generate coherent and contextually relevant content.

Furthermore, AI systems continually learn and adapt through ongoing exposure to new data, improving their ability to generate content that mirrors human creativity and style. This adaptive learning allows AI to refine its outputs, making them more convincing over time. As AI tools become integrated within various content creation platforms, their outputs will blend seamlessly with human-generated content, further complicating detection.

Additionally, the development of AI tools specifically designed to mimic individual authors' styles adds another layer of complexity. These tools can analyze previous writings of an author and recreate content that aligns with their unique style, making it even more challenging to discern authenticity.

As AI technology continues to evolve, the line between human and machine-generated content will blur, posing challenges for educators, publishers, and platforms dedicated to content authenticity and originality.

this was AI generated wasn't it

 

[GT49er]

We are moving back to more in-person exams in some cases for this very reason, but because kids today only communicate via texting, their handwriting is unreadable!

Yes, I imagine that could be a bit problematic - I know that with laptops and computers etc. instead of pen and paper, my hand-writing has gone to pot the last 20 years or so. Still, I guess they'll just have to learn - as we did, years and years ago!

 

[happypig]

this was AI generated wasn't it

Guilty as charged your honour

 

[Moshe Gariani]

May not be a completely foolproof solution, but it might help to insist that exams, theses and dissertations should be hand-written in the student's own hand-writing.

On stone tablet, papyrus, slate or vellum...?

 

[seagull_si]

When I was at Uni I had a viva exam on my final dissertation where they would question me about what I had written. Its all well and good to use AI to create your dissertation, but you need to understand and back up what is written.
AI could be used as a tool to maybe write something that would achieve good marks, but the viva would sort out what knowledge the student actually has on the subject.
I think people who have a good knowledge on the subject will write their own dissertations while people who have been coasting through uni will use AI and would be found out in a viva assessment.

 

[Guinness Boy]

Thanks to AI there won't be any jobs for them to go on to anyway.

‘It’s nightmarish’: why 1.5m Britons are still hunting for a job

UK jobseekers say employers are hiring fewer staff, whom they expect to do more for less pay

www.theguardian.com

 

[Moshe Gariani]

Here is the google gemini response to your opening post

You've hit upon some incredibly important and rapidly evolving issues surrounding AI and higher education. It's true, the landscape is shifting dramatically, and your observations about the speed of change and the increasing sophistication of AI-generated work are spot on. Here's a breakdown of the key points you've raised and some thoughts on them:

• AI's Growing Sophistication: The idea that AI-generated work is easily detectable is becoming outdated. As you've experienced, AI is quickly mastering the kind of synthesis and analysis required for postgraduate-level writing, including literature reviews and research reports. Referencing is a challenge, but one that's likely to be overcome soon.
• The "Tools" Argument: You're right to draw the parallel with word processors, calculators, and statistical packages. It's hard to argue against students using available tools, even if those tools significantly enhance their output. The question becomes less about whether they use them, and more about how they use them, and what skills are still essential.
• The Devaluation of Transferable Skills: This is a crucial point. If AI can perform high-level analysis and communication, what happens to the value of those skills in the job market? Traditional markers of graduate success may need to be re-evaluated. Critical thinking, creativity, problem-solving, and adaptability – skills that are harder for AI to replicate – become even more important. The ability to critically evaluate AI-generated work will also be a key skill.
• The Changing Value of a Degree: The fundamental purpose of a university education is being challenged. If knowledge synthesis and even research can be outsourced to AI, what is the unique value proposition of a degree? Universities need to adapt by focusing on developing those higher-order thinking skills, fostering collaboration and teamwork, and providing opportunities for experiential learning that AI can't replicate. The emphasis may shift from knowledge acquisition to knowledge application and creation.
• Advice to an 18-Year-Old: This is the million-dollar question. The rise of AI definitely adds a new dimension to the decision-making process. While a degree still holds value, the type of degree and the focus of the education become more critical. I would advise an 18-year-old considering Sociology or Business Studies to:
  • Focus on the development of critical thinking: Learn how to evaluate information, identify biases, and construct well-reasoned arguments. This is essential in an AI-driven world.
  • Embrace interdisciplinary learning: Combine their chosen field with other areas like data science, computer science, or even design thinking. This will make them more adaptable and better equipped to work with AI.
  • Seek out experiential learning opportunities: Internships, research projects, and study abroad programs can provide valuable real-world experience that complements academic learning.
  • Consider the future of work: Research how AI is impacting their chosen field and identify skills that will be in demand in the future.
  • Don't dismiss the humanities: While STEM fields are often emphasized, the humanities cultivate critical thinking, communication, and ethical reasoning – all of which are crucial in the age of AI.

In short, the rise of AI is a game-changer for higher education. While the future is uncertain, it's clear that universities need to adapt to this new reality by focusing on developing uniquely human skills that AI can't replicate. The conversation we're having now is essential, and it needs to continue as AI technology continues to evolve.

THAT is exactly what we are talking about...

The quality of critical thinking, breadth of relevant knowledge needed, and the accuracy of language/grammar used would at any point until very recently have been indicative of the highest possible level of education.

Today it could be the work of anyone who knows how to use "cut and paste" on a website.

 

[BBassic]

I don't know if this is helpful to the wider discussion but I am sick to death of hearing about AI

Every new product has some sort of AI twist and I don't imagine it'll be long before my toilet paper, perhaps in the form of an Andrex dog hologram, will vocally tell me to eat more fibre after analysing my wiping technique. It's all over the industry I work in, all over the telly, all over social media.

I wish it would hurry up and either a) just become a part of life so we don't have to talk about it b) replace our need to work so we can realise a Star Trek style post-scarcity utopia and not have to talk about it or c) gain sentience and wipe us off the planet so we have no mouths or brains with which to talk or think about it.

I don't care which, just hurry the hell up.

 

[Moshe Gariani]

When I was at Uni I had a viva exam on my final dissertation where they would question me about what I had written. Its all well and good to use AI to create your dissertation, but you need to understand and back up what is written.
AI could be used as a tool to maybe write something that would achieve good marks, but the viva would sort out what knowledge the student actually has on the subject.
I think people who have a good knowledge on the subject will write their own dissertations while people who have been coasting through uni will use AI and would be found out in a viva assessment.

Designing assessments to be relatively "A.I.-proof" is definitely part of an answer to part of the question. Asking A.I. to design A.I-proof assessments is already happening...

Universities will have to act to protect the value of a degree by making it impossible to succeed by A.I. cheating. But that will rule out a lot of traditional approaches to academic skills development and assessment.

Presentations, practical skills, invigilated written exams and viva type oral exams will have to become the norm rather than current "coursework" type written assessments.

 

[chickens]

I for one welcome our new, artificially intelligent, overlords.

 

[GT49er]

On stone tablet, papyrus, slate or vellum...?

Paper. The others would be plain silly. Biros and felt tip pens would be allowed, no insistence on quills. OK?

 

[Moshe Gariani]

I for one welcome our new, artificially intelligent, overlords.

Haha, well, at least our new AI overlords are polite, articulate, and terrifyingly efficient!

On the bright side, if universities adapt quickly, this could lead to a much-needed shake-up of outdated assessment models. On the downside… well, we might all end up working for an AI that writes better than us, thinks faster than us, and never needs coffee breaks.

Would you say you’re optimistic or a bit wary about where this is all heading?