An AI Enabled Polymath
A Guide to Practical AI
Welcome to Polymathic Being, a place to explore counterintuitive insights across multiple domains. These essays take common topics and investigate them from different perspectives and disciplines to uncover unique insights and solutions.
Today's topic is my answer to
from who recently asked: "Can Generative AI make us all Polymaths and company founders?" This essay was first published on his substack under a similar title and is modified here to focus more on enabling polymathic thinking.
Introduction:
As a quick baseline to remind everyone what a Polymath actually is!
A Polymath (Greek: πολυμαθής, polymathēs, "having learned much"; Latin: homo universalis, "universal human") is an individual whose knowledge spans a substantial number of subjects, known to draw on complex bodies of knowledge to solve specific problems.
Fundamentally, I view this as an aspirational goal to reconceptualize the world around us. This allows me to draw from a broad array of fields to solve complex problems. I’ll point out that this definition doesn’t necessarily imply mastery per se. but knowledge.
So what’s the angle, if not mastery? As I explored in a previous essay on Systems Thinking, I think it boils down to three things:
Insatiable Curiosity
The humility to accept we don’t know as much about the problem(s) as we think
Intentional reframing of the problems to see if we understand them completely
Anyone who claims that being a Polymath is an end state misses the core element of being a Polymath: the journey never ends. Therefore I am an Aspiring Polymath.
Can AI make me a Polymath?
I think the introduction sets a solid tone on the mindset behind being a Polymath. AI can’t help you with that mindset, but it does provide a useful tool for executing that mindset. So what might this look like?
AI tools like the new Large Language Models (LLMs) provide pretty solid methods to challenge our own biases and to expand beyond our own domains of expertise. If used properly…
For example, Ethan Mollick and Lance Cummings writing for
and respectively, offer keen insights on properly using AI in academia and life as well as better ways to prompt AI to get better results.A few tricks I’ve used to help me explore new areas uses Lance’s prompt structures and plays around to get new insights. For example
Prompt: I am an expert in [technical field] and I am exploring how to solve a problem that involves [insert problem here]. Please provide a list of other technical fields that are facing similar problems. Output a list of technical fields, problem definitions, and why you think they are related.
I like to run between ChatGPT and Bing with ChatGPT to build out the actual web resources to follow up on. It’s also fun to use the AI to help figure out the right questions to ask or considerations to answer!
(I should have asked ChatGPT this at the start but here’s the response now… It confirms I’m hitting the points and adds a few more that you can explore later!)
Prompt: I am writing an essay about whether AI can make people a polymath. What are a list of considerations I should prepare to discuss?
ChatGPT: Exploring the potential of AI in making people a polymath (someone who is knowledgeable in many different subjects) is a fascinating topic. Here are some considerations you might want to discuss in your essay:
Definition of a Polymath: Begin by defining what it means to be a polymath. Is it simply about gathering knowledge across various subjects, or does it also entail a deep understanding and original thought in multiple domains?
AI as a Learning Tool:
Customized Learning: AI can offer personalized learning experiences, adapting to an individual's pace and preferences.
Broad Access: With AI-driven platforms, one can access vast amounts of information on diverse subjects, potentially faster than traditional methods.
Human Curiosity and Drive:
Even with the best tools, the human drive to learn and be curious is crucial. Can AI inspire this intrinsic motivation or just facilitate it?
AI’s Role in Synthesizing Information:
Being a polymath isn't just about knowing a lot; it's about connecting ideas from different fields. Can AI aid in synthesizing and interrelating concepts from disparate domains?
The Role of Human Experience:
Much of what polymaths know comes from life experiences, intuition, and tacit knowledge. Can AI replicate or complement these human aspects?
Potential Over-reliance on AI:
If people lean too heavily on AI for information and insights, does it reduce their own analytical and critical thinking skills?
Cognitive Offloading:
If we rely on AI to remember or process information, are we offloading cognitive functions and thereby, in the long run, hindering our potential to become polymaths?
Lifelong Learning and AI:
Polymaths are often lifelong learners. How can AI support continuous learning throughout one's life?
By exploring these considerations, you can craft a well-rounded essay that delves deep into the capabilities and limitations of AI in the quest to cultivate polymaths.
I was right on track and ChatGPT gave me some more things to consider such as the implications of cognitive offloading, accessibility and equity, and the human dimensions of AI and a Polymathic Mindset.
Other resources are helpful like Perplexity.ai which has good source material but works better when fed prompts refined by ChatGPT. Also, tools such as WordTune and their ‘spices’ actually allow you to add data, analogies, and other tools to help bolster writing and expand that Polymathic Mindset such as the ability to create a counterargument.
This tool is useful specifically if I’m writing something where I have a stronger bias. To get out of my own brain-space I will run counterarguments against all my main points. The AI often provides pretty good material that challenges me to rethink or rephrase my point to make it more impactful.
AI can definitely help augment a Polymathic Mindset if we use it to challenge, explore, and illuminate areas outside of our explicit domains and disciplines. The key to remember is that it can’t get you into that mindset to begin with.
Applying Polymathic Thinking to Founding a Company
The original question by Mr. Spencer asked if AI could help make us company founders. That answer is simply “No.” AI cannot make you a company founder.
However, company founders do best when they embrace a Polymathic Mindset and balance three critical elements of organizational success focused on maturing:
Products: Transitioning from feature push to scalable pull.
Processes: Evolving from Ad-hoc bottoms-up to disciplined, agile, and aligned.
People: Maturing from scrappy to elite.
Success starts with the mindset first and requires much more discipline, charisma, and grit than what AI is capable of doing. In fact, being a company founder is something that is uniquely human and is not likely to be replaced by AI anytime in the near future.
Conclusion
AI is a great enabler, a co-creator, a valuable critic, and a tool that can challenge your assumptions. The key to using AI in any context is to leverage the superpowers that make us human that AI cannot replace, and then weave AI in as an enabler.
It all starts with understanding who we are as humans, how we can think differently with, or without AI, and then complementing our continued growth and development to achieve extraordinary results.
I’d love your feedback and insights because, as useful as AI is in some ways, it just doesn’t beat the real perspectives of humans collaborating and building great things, ideas, and relationships.
Check out these other essays for more insights on AI and company leadership:
Enjoyed this post? Hit the ❤️ button above or below because it helps more people discover Substacks like this one and that’s a great thing. Also please share here or in your network to help us grow.
Polymathic Being is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.
Further Reading from Authors I Appreciate
I highly recommend the following Substacks for their great content and complementary explorations of topics that Polymathic Being shares.
- All-around great daily essays
- Insightful Life Tips and Tricks
- Highly useful insights into using AI for writing
- Integrating AI into education
- Computer Science for Everyone
I already spend so much pleasant time considering how everything, absolutely everything, is connected. I had pushed AI aside. I've now decided that the children I am raising will benefit from an intuitive use of LLMs. Now I am enjoying polyhistor-ical information in a polyh-ysterical way. Possibly malevolent! It isn't as if I could make anyone think me more odd than their already raised eyebrow signals. Hopefully, you've already become acquainted with @losttools , here in these fine stacks. Early education meeting AI. Weaponized ADHD is a battle skill.
great piece! i have a couple of thoughts with a diff pov.
current llms are not only unreliable narrators (hallucinations et al) - they mostly regurgitate versions of what they’ve seen occur in statistically significant ways.
and we don’t yet know how to build models that can connect multiple sources of knowledge in a previously unseen manner.
given that - i would argue that the ai systems of today are only good at helping us automate workflows in a non-brittle fashion vs providing novel insight across domains.