Understand the Implications of Generative AI in Education
Bans aren’t the answer, but what is?
Generative AI is disrupting models across industries, and classrooms around the world are already grappling with the change. Concerns have been raised about its effects on education and student learning, with cheating being a primary concern.
Yet, getting past the concerns and looking to the future, generative AI can transform education just as past technologies such as calculators and the internet have. IT will have to guide the response to generative AI, which will have implications from the classroom experience to the institution’s policies.
Implications for IT leaders in the short, medium, and long term
IT and business leaders will need to be strategic and address the concerns and questions of educators who want to limit cheating and executives who want to know the policy implications for generative AI tools.
- Limit risks more effectively: IT leaders can provide more meaningful solutions than bans or plagiarism detection tools that don’t work.
- Extract value across the board: Students, faculty, and administrative staff can benefit from the value generative AI has to offer when it’s embedded strategically.
- Prepare for legislation and policy building: IT leaders will have the mandate to build clear internal policies and help comply with new legislation on generative AI.
Member Testimonials
After each Info-Tech experience, we ask our members to quantify the real-time savings, monetary impact, and project improvements our research helped them achieve. See our top member experiences for this blueprint and what our clients have to say.
9.0/10
Overall Impact
$19,000
Average $ Saved
16
Average Days Saved
Client
Experience
Impact
$ Saved
Days Saved
St. Lawrence College
Guided Implementation
10/10
$19,000
16
None
America-Mideast Educational and Training Services, Inc.
Guided Implementation
8/10
N/A
N/A
Informative session. Thank you
Understand the Implications of Generative AI in Education
Bans aren't the answer
Analyst Perspective
Guide the appropriate use of generative AI in teaching, learning, and working.
Generative AI has emerged as a prominent technology, garnering substantial attention in a very short time. The advanced functionality of generative AI for searching and creating content has raised concerns about its implications in education. Info-Tech Research Group has undertaken an examination of the impact of generative AI on education, offering insights into the future implications for educators, students, and IT professionals.
The use of generative AI raises concerns about its effects on education and student learning, with cheating being a primary concern. Nonetheless, the technology has the potential to transform the classroom just as calculators, the internet, and digital assets changed the way we taught and learned in the past. Educators may have no choice but to embrace generative AI and leverage its strengths to enhance learning and development.
Mark Maby
Research Director for Education, Industry Practice
Info-Tech Research Group
Understand the implications of generative AI in education
Generative AI
- ChatGPT reached 100 million users in just two months after launching.
- ChatGPT is generative AI, and like other technologies before, it will have substantial ramifications on education.
- Understand the implications of generative AI in the short, middle and long term.
| Short term | Mid term | Long term |
|---|---|---|
|
The response to cheating:
|
Benefits to education:
|
Long term
|
Identify high-value processes
- Identify your capabilities that support key business processes based on the whether they are conversational, repeatable, and valuable.
- Build a heatmap, highlighting areas where a generative AI solution could be effective.
Info-Tech Insight
IT will need to provide guidance on the proper response to generative AI, which will change how we teach, learn, and work in education.
OpenAI and ChatGPT: An overview
“I think it's incumbent on those of you in IT … to spread the word broadly, not in a semester, but now. We need to let our clients know what this is, what the future is likely to be, and how they may use it without jeopardizing the quality or rigor of their teaching.”
Ray Schroeder on ChatGPT,
UPCEA Senior Fellow and UIS Professor Emeritus (Educause, January 30, 2023).
| 1 | ChatGPT (generative pretrained transformer) was created by OpenAI, a non-profit set-up in 2015 (Web Archive, April 27, 2016). Since 2019 Microsoft has been a major investor in OpenAI’s for-profit subsidiary (CNBC, January 10, 2023). |
| 2 | GPT 3.0 expresses a 175 billion parameter neural network (Towards Data Science). This level of sophistication can only be created by organizations with billions of dollars of funding. |
| 3 | GPT uses three approaches to machine learning:
|
| 4 | ChatGPT (GPT 3.5) is specifically designed to serve a chatbot function. Its logic abilities are likely augmented by Codex, OpenAI’s coding tool (OpenAI). |
| 5 | ChatGPT is generative AI; unlike your standard chatbot, which excels at executing basic workflows, ChatGPT can create new content based on inputs. |
| 6 | ChatGPT reached 100 million users in just two months after launching (Reuters, February 2, 2023). |
Short term tactics: ChatGPT and Cheating
What have been the responses to ChatGPT among faculty and leadership at your institution?
Blocking sites on the institution’s network
Prominent institutions have blocked ChatGPT on their network. This has mostly been at the K-12 level, including New York City PS in the US and Queensland and NSW in Australia (Education Week). Sciences Po in France is an example at the university level (Reuters, January 27, 2023).
Limited Effectiveness: 95% of students have mobile phones to access ChatGPT (Pew Research Center).
Risks: Prevents creative use of the tool by innovative teachers.
Plagiarism-detection tools
Tools can assess authenticity of a text as human-written or AI-generated. Turnitin is a prominent example but there are other tools, including one offered by OpenAI. The company is even an attempting to statistically “watermark” its output (TechCrunch).
Limited Effectiveness: These tools provide a confidence metric, and AI will likely improve its “naturalness”.
Risks: These tools come with their own privacy issues. Also, students will become suspicious of their teachers who act suspicious toward them.
Blocking sites at the level of the device
Higher education testing centers and labs can be used as dedicated centers for written assessment where access to ChatGPT is blocked.
For instructors grappling with flagrant use this may be an option.
More effective ways of assessment likely exist, such as oral discussion.
About Info-Tech
Info-Tech Research Group is the world’s fastest-growing information technology research and advisory company, proudly serving over 30,000 IT professionals.
We produce unbiased and highly relevant research to help CIOs and IT leaders make strategic, timely, and well-informed decisions. We partner closely with IT teams to provide everything they need, from actionable tools to analyst guidance, ensuring they deliver measurable results for their organizations.
What Is a Blueprint?
A blueprint is designed to be a roadmap, containing a methodology and the tools and templates you need to solve your IT problems.
Each blueprint can be accompanied by a Guided Implementation that provides you access to our world-class analysts to help you get through the project.
You Get:
- Generative AI use cases for students, faculty, and administration.
- A deeper understanding of the risks and opportunities of generative AI in education.
- Generative AI capability maps for K-12 and higher education.
Talk to an Analyst
Our analyst calls are focused on helping our members use the research we produce, and our experts will guide you to successful project completion.
Book an Analyst Call on This Topic
You can start as early as tomorrow morning. Our analysts will explain the process during your first call.
Get Advice From a Subject Matter Expert
Each call will focus on explaining the material and helping you to plan your project, interpret and analyze the results of each project step, and set the direction for your next project step.
Unlock Sample ResearchContributors
- Xavi Herce, Chief Revenue Officer at Fermat / Batou XYZ
- Matt MacLeod, Embedded Firmware Engineer at Rainhouse Canada
- Insight from two Roundtable discussions hosted by Info-Tech Research Group.
