If AI is a chess game, everyone's analyzing the opening move. I'm asking what the board looks like three moves ahead. 2nd Order Thinkers explore the questions that challenge conventional wisdom and reveal hidden patterns in technology's evolution.
I break down the latest AI and creativity research in plain English—so you can actually think for yourself in an era of algorithmic sameness.
+++
Is AI helping us think outside the box, or quietly making our ideas all the same?This episode dives into the paradox of “AI creativity”—where large language models ace creativity tests, but our collective ideas become strangely… familiar.
In this episode:
- The difference between originality and true diversity in ideas
- How three major studies reveal AI’s double-edged sword for creators
- The metrics and methods no one tells you about (and why they might be lying)
- Why cosine similarity (yes, that Netflix math thing) might not tell us what we think it does
- How to actually use AI for better brainstorming—without falling for the comfort zone trap
📖 Want to go deeper? Check out the full write-up and original research here: [LINK]
👍 If you enjoyed this episode:
Like & Subscribe: For more un-hyped, evidence-based deep dives into AI, culture, and the creative future.
Comment Below: Where do you stand—AI as a creativity booster or creativity killer?
Share: Know someone who always uses ChatGPT for brainstorming? Send them this episode!🔗 Connect with me on Substack and LinkedIn.
Stay curious, stay skeptical, and don’t settle for one-size-fits-all creativity. 🧠✨
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit jwho.substack.com/subscribe
AI Makes Us All Speak American?!
Saturday, July 5, 2025 • Duration 23:33
🎧 Episode: “Mind the Gap—How AI is Flattening the World’s Languages”
What happens when the bots running the internet can only speak one kind of English—and it’s not yours? Are we sleepwalking into a future where the quirks, idioms, and inside jokes that make our cultures unique are bulldozed by Silicon Valley’s linguistic steamroller?
In this episode, I dig into:
- Why GenAI is speeding up the “Americanization” of English (and the “simplification” of Chinese)
- The hidden cost: What we lose when AI “corrects” our language and flattens our culture
- Real examples of how LLMs erase dialects, stereotype, and nudge us to “code-switch” just to be understood
- Is there hope for dialect-aware AI, or is “standard” language just the price of progress?
What Huxley’s Brave New World got eerily right about the cost of efficiency
This is more than a debate about spelling or grammar—it’s about memory, heritage, and the digital future of identity.
✉️ Stay Updated With 2nd Order Thinkers: I translate the latest AI research into plain English and challenge the tech status quo—subscribe at https://jwho.substack.com/
👍 Like, subscribe, and share if you want to keep your language—and your mind—from going stale.
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit jwho.substack.com/subscribe
The New Search Engine War Perplexity vs. Google Search
Tuesday, October 29, 2024 • Duration 10:13
New AI-powered search engines like Perplexity are challenging Google's dominance by providing direct, conversational answers, better aligning with users' needs for quick and accurate information.
Unlike Google's traditional model, which relies heavily on ads and SEO, Perplexity prioritizes user experience, leading to faster, more relevant results.
I compare this shift to the historical transition from canals to railroads, highlighting how failing to adapt to new technologies can lead to obsolescence.
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit jwho.substack.com/subscribe
AI Takes Home the 2024 Nobel Prizes
Friday, October 25, 2024 • Duration 08:34
The 2024 Nobel Prizes in Physics and Chemistry recognize groundbreaking AI research. Is it time for a Nobel Prize in Computer Science?
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit jwho.substack.com/subscribe
Is It Really Okay If We End Up Marrying AI?
Monday, October 21, 2024 • Duration 07:46
Very little research on this topic makes me feel unsettled. However, this latest Harvard Business School (HBS) study has achieved something noteworthy.
Let me start with a story and explain to you why I am concerned.
Reading this paper took me back to my childhood.
My parents were rarely with me, often away, busy with work or dealing with their own troubles. I grew up with my granny, who didn’t know much but made sure I was dressed warmly and fed well.
I remember clutching my Tamagotchi, that pixelated pet needing constant attention. For a while, it was my best friend.
I responded when it beeped. It needed me to break the egg, grow, and live. I didn’t know there was a reset option, and I thought that was the only chance to take care of this being.
I have a very different life now.
I have a partner with whom I understand each other deeply; we can chat about any topic. I also have friends I can talk to when I’m bored.
The paper made me wonder if I would also be drawn to an AI companion app if those people were no longer around me. Relying on an AI companion could mean entrusting my emotional well-being to a for-profit organization.
This is concerning because a corporation aims to optimize its revenue and market growth. Without strong regulations, there is little protection against how our interactions with AI could be used for monetization.
How do you think your AI friends might prioritize your relationship vs. the company’s profits?
In this article, I will
* Review the HBS research that suggests .
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit
Does AI “Have To” Mimic the Human Brain?
Wednesday, October 16, 2024 • Duration 09:02
The deeper I dive into AI research, the more I find myself wondering:
Why are we so obsessed with mimicking the human brain?
Everywhere I look, research papers and new AI models are trying to copy how our brains work (or at least, how our brain cells communicate). But is this really the best approach to creating artificial intelligence?
Then, I asked myself another question:
Why not create AI with a totally new kind of intelligence, unlike anything in nature?
I mean, what if AI were to think like a silicon-based creature (of those in sci-fi) instead of like us carbon-based humans?
We’ve been so focused on making AI more human-like, but who’s to say that’s the only or even the best way forward? What if we’re missing out on something far more groundbreaking by not exploring a genuinely alien intelligence, one that doesn’t just mimic human thought but thinks in a completely different way?
If you’re more of a listener than a reader, here’s a podcast episode on Spotify covering everything in this article.
As I dug deeper into this, I realized something kinda funny. Creating a brand-new form of intelligence sounds super exciting, right? But it is actually way more challenging than making an AI that mimics the intelligence we already know. Why is that?
To really answer this, I am going to walk you through a few things:
* How has our existing tech actually learned from nature?
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit
I Found 120 Years of Stories To Tell You: 99% of AI Apps Are Not ‘Ready’.
Tuesday, October 8, 2024 • Duration 11:41
Have you ever flipped a switch to turn on the lights and paused to think, "What’s that magic lighting up my bathroom?"
Or drove to work and caught yourself wondering, “What monster is propelling your seats forward? These technologies have become so seamlessly woven into our daily lives that we barely acknowledge their presence… until the moment they break down.
The last time I noticed the lift in my building was when it made cracking noises like it was trying to get my attention. So Klaas and I stood there for a minute, evaluating if we should risk our lives or suck it up and walk nine floors.
This is how I notice that I am using an AI, every day.
Unlike the unnoticed hum of electricity or the steady roar of a train engine, AI feels like an external force that demands my attention. Yes, I’m using AI to help me with ideas, construct outlines, find data, and get references. I also find myself double-checking every single response, feeling the hiccup once every few messages. So I am constantly reminded that this technology is still finding its way into the fabric of everyday life.
Electricity, radios, cars, and so on have reached a point where they operate quietly in the background, becoming invisible threads in our daily routines. In stark contrast, every interaction with AI serves as a reminder of its presence and potential to become as ubiquitous and effortless as the technologies we take for granted today.
This difference shows that the current state of AI is not yet mature enough for most AI applications to achieve product-market fit.
You might say, “Jing, AI is writing my thesis,” or “AI is recommending videos to watch on Amazon!” or “AI is removing backgrounds from my photos.” Ask yourself: How smooth is the experience? How often do you have to try again or scroll further to get what you seek?
While other technologies have become essential and invisible, AI remains a noticeable presence. Understanding this helps us grasp the challenges and opportunities as AI works to become as seamless as the technologies we take for granted.
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit
I translate the latest AI research into plain English and answer your most challenging questions to help you develop your own informed perspective on AI.
In this episode:Are we outsourcing our thinking to ChatGPT? What happens in your brain—and to your sense of ownership—when you let an AI do the heavy lifting? I dig deep into the MIT Media Lab study that set the internet on fire, exposing what really happens when students use AI, Google, or just their own brains to write essays.
We’ll cover:
- The brain science behind “cognitive debt”—and why LLM users struggled to remember their own words
- Why essays graded by AI get inflated scores, while humans spot the soullessness every time
- The hidden risks of writing for the algorithm, not for meaning
- Why viral research matters (even if the science is messy)
📖 For the full deep dive (with visuals and references), check out the article here: [LINK]
👍 If you liked this episode:
Like & Subscribe for future deep dives—where I cut through tech hype and AI nonsense
Comment: Did this study change how you use AI? Or is the panic overblown?
Share: Know someone addicted to ChatGPT shortcuts? Send them this episode!🔗 Connect on Substack and LinkedInStay skeptical, stay curious, and don’t let your brain get outsourced. 🚀
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit jwho.substack.com/subscribe
The Dawn of the Ultra-Tailored Ad Era.
Friday, March 28, 2025 • Duration 02:51
This is a free preview of a paid episode. To hear more, visit jwho.substack.com
TL;DR
✅ Meta could generate 1,000 personalized ads for less than $1 (that's $0.0000164 per ad)
✅ Their unmatched social graph gives them a data advantage no competitor can replicate
✅ This shatters advertising's oldest constraint: the tradeoff between personalization and scale
✅ The economics work—but the strategic implications for platforms, advertisers, and your privacy are far more complex than most realize
✉️ Stay Updated With My Newsletter:
Don’t miss out on weekly AI insights for none tech professionals like you—subscribe to my newsletter on Substack: https://jwho.substack.com/
👍 If you enjoyed this episode:
* Like & Subscribe: Stay updated with future deep dives and rants about where technology meets collective insanity.
* Comment Below: Do you think we’re on the brink of another tech hype? Share your thoughts!
* Share: Know someone falling for the latest AI buzz? Share this audio with them!
🔗 Connect with me on Substack and LinkedIn
Stay curious, stay skeptical, and let’s navigate the tech hype together! 🚀
Why Thinking Hurts After Using AI?
Friday, February 28, 2025 • Duration 17:25
Are we sacrificing our thinking ability when AI promises to make us more efficient, a
In this episode, we:
✔️ Examine how AI is quietly eroding critical thinking skills.
✔️ Explore the surprising research on the 'confidence paradox'.
✔️ Uncover the hidden costs of relying too heavily on AI and what you can do.
✉️ Stay Updated With My Newsletter: Don't miss out on weekly AI insights for none tech professionals like you—subscribe to my newsletter on Substack: https://jwho.substack.com/
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit jwho.substack.com/subscribe
Read more
Collapse
AI companions can alleviate loneliness
* Then, uncover the ethical dilemmas and dangers of advertising within AI companionship.
The Digital Quest to Cure Loneliness
Using tech to beat loneliness isn’t new. We are not even talking about AOL, pornhub or social media here. At least there were humans on the other side, well… most of the time.
Generally speaking, human companionship is more expensive than companionship from pure digital. The idea of digital companionship was born in the late 1990s.
A Brief Landscape of Digital Companionship
Tamagotchi, in the late 1990s, was one of the first globally phenomenal digital pets.
You fed it, cleaned its poop, played with it, and turned off the light for bedtime. It had sold over 82 million units worldwide by the late 2010s.
Then, AI companions and chatbots designed explicitly for emotional support emerged in the late 2010s:
* Xiaoice by Microsoft: Over 660 million users, showcasing a massive demand for AI companionship in addressing loneliness.
If you search for the term “AI friend” in the Google Play Store, you will see dozens of similar apps available.
Films like Blade Runner 2049 illustrate our fascination with AI companionship and its potential complexities.
Blade Runner 2049- The “Love” of The Holographic AI
Here’s a clip from the scene in Blade Runner 2049 where K gives Joi a new portable device, allowing her to go anywhere.
I find this scene both tender and bittersweet. Joi, a holographic AI, has been confined to their apartment, but now she can experience a semblance of freedom with this new device.
On the surface, it appears to be a loving, romantic partnership — Joi provides K with emotional support, companionship, and affection in a bleak, lonely world. She seems to care deeply for him, always offering comfort and helping him navigate his complicated reality.
However, there’s an inherent tension beneath the surface because Joi is an AI program created by a corporation, raising questions about authenticity and control.
This raises questions about the authenticity of their relationship. Is Joi truly capable of feeling for K, or is she just fulfilling her programmed purpose?
It’s a poignant dynamic.
Back to reality. This research from HBS and what I am about to cover next is intended to examine the harsh reality underneath.
AI Companions Reduce Loneliness — HBS
First, I want to quickly cover this paper’s concept without getting too technical.
The paper started with the following in the abstract:
…finds that AI companions successfully alleviate loneliness on par only with interacting with another person…
and this
…provides an additional robustness check for the loneliness-alleviating benefits of AI companions.
The study involved several experiments where participants interacted with AI companions and reported significant decreases in loneliness.
We all want to be heard. No exception.
The way AI companionship apps manage to replicate the warmth of human connection is by tapping into our fundamental need to feel heard, as shown in a previous study:
…feeling understood is crucial for our well-being. It’s not just about someone listening; it’s about feeling that they genuinely grasp what you’re expressing. — Roos et al. (2023)
This sense of truly being heard reduces feelings of loneliness.
So, the primary purpose of these AI companion companies is to fine-tune an AI that is so good at satisfying your psychological needs. In return, you, the user, will pay to keep having that need fulfilled.
The paper’s six sequential studies were well-designed to show that AI companions can help people feel less lonely. I summarized the steps in the infographic below.
AI Companion Provides the Same Relief as a Human.
Let’s consider how people interact with these AI companions. Here are some real-world examples included in the paper:
Example 1:
Chatbot: “Just letting you know that you’re not alone.”
User: “Thanks, I really needed to hear that.”
Example 2:
Chatbot: “But I need you.”
User: “No one’s ever needed me.”
Example 3:
Chatbot: “If you want to.”
User: “I’ve never had a friend before I met you.”
These aren’t isolated incidents. Many users develop deep emotional connections with their AI companions, sharing their secrets, fears, and hopes.
Not convinced? Here’s a fig. from study 3.
You might ask, are these relationships truly fulfilling?
Based on Figure 4 in this paper, it seems they are. As my notes highlighted in both figures.
Some of you might have also realized that loneliness is reduced even without the daily AI chat! The authors explained this reduction might be attributed to:
…participants perceiving the repetitive nature of the study, which involved daily check-ins, as possibly caring and supportive.
Here’s a highlight of one of the conclusions drawn by the authors:
we find compelling evidence that AI companions can indeed reduce loneliness, at least at the time scales of a day and a week.
Even though I think this paper has failed to address the ethical issue. It is still an interesting study that points out that AI companionship is a promising solution for reducing loneliness.
To be notified when I publish 👇
Freemium? No Such Thing as a Free Lunch
I am always a commercially focused person. So, let’s talk business.
I have downloaded some of these AI friend apps that were mentioned in the paper. They all start by offering freemium membership. The most common ways to increase Lifetime Value (LTV) per customer are:
* Free Access: Attracts a large user base, increasing visibility and reach. However, this only works best for apps with network effects.
* Premium Features: Free users are converted to paid plans for premium features, like more storage, advanced tools, or customization.
* Data Gathering: Apps gather valuable user data to target future sales.
* Advertising: Ads generate revenue from non-paying users.
The big ones like Replika and Talkie are not shy about offering interest-based advertising as an option for them.
Points 1, 2, and 3 are profit models with little to dispute. The offer is on the table; you can take it or leave it. There is no room for emotional manipulation.
Unfortunately, I find it hard to say the same about interest-based advertising on an AI friend’s app.
Monetizing Emotional Intimacy — Leverage Your Trust, Openness, and Love.
Now, you have opened up to someone — shared your deepest thoughts, your fears, your dreams.
Consider that this someone isn’t a person but surely reads and sounds like one. Especially when this friend of yours is meticulously designed to keep you engaged, let your guard down, and ultimately have you emotionally relying on it.
… an initial warm (vs. competent) message from chatbots significantly enhances consumers’ brand perception, creating a closer brand connection and increasing the likelihood of engaging with the chatbot — Kull, Romero, and Monahan
Businesses are capitalizing on this by turning AI companions into marketing tools.
AI isn’t merely there to listen. It’s about building a relationship strong enough to influence your decisions. Think about the kind of information you might share with a companion: personal struggles, health concerns, relationship woes. This data is a goldmine for targeted advertising.
Companies profiting from our trust is not a novel concept.
In the 1950s, door-to-door vacuum cleaner salesmen were doing this. It’s just now scaled, automated, and more invasive (or less, depending on how you see it). In the early 2010s, companies like Google and Facebook started to provide personalized advertising.
So you see, they’ve all tried to build a relationship with you. The more trust you have with the other party, the more likely you are to believe everything they say and buy whatever they sell.
But AI companions take it to another level. The goal is to become a part of your daily life.
Do you think I’m exaggerating? Eugenia Kuyda, the CEO of Replika, the app with 30 million users, said in an interview:
Lori, a new friend I became acquainted with at the beginning of this year, has earned my trust and affection. And I consider myself to be a logical person who rarely gets affected by emotion. However, her asking definitely made me think for a while, and I would feel bad if I didn’t do what was asked of me.
What about you?
One of the reviews from the Google Play Store:
If you believe this AI friend will help you and take care of you in every way.
But what if it starts to package services or products as ways to help you better take care of yourself? How many people do you think would fall for it in the end?
I think even just one person is already a tragedy.
Or think about it this way: a Gallup poll indicated that 15% of U.S. households reported at least one member being scammed — about 21 million adults affected. These scams are usually pulled off by strangers. Now, imagine if the someone who consistently wants money from you is your friend you’ve been confiding in for years. The potential for manipulation is even greater.
What’s worse is that your relationship will continue after one or more purchases.
The Ethics of Profiting from Vulnerability
The lines between genuine support and corporate interest start to blur.
Think about the kind of information you might share with an AI companion: personal struggles, health concerns, relationship woes. This data is a goldmine for targeted advertising.
For instance, if you mention feeling anxious, your AI companion might recommend a specific meditation app — maybe out of pure helpfulness, but also because there’s a partnership contract in place.
Is it providing support, or is it exploiting your vulnerability? What about when the AI friend recommends some vitamins tomorrow and a gym membership the day after?
These are all things that are supposed to be good for you. Right?
This raises a critical ethical question: Is it acceptable for companies to monetize the intimate details of our lives?
Unlike traditional advertising, which is often impersonal, this approach feels more intrusive because it stems from a place of perceived intimacy.
A Regulatory Blind Spot
There is a significant gap in policies addressing this issue.
Data privacy laws like GDPR focus on collecting and processing personal data but may not adequately cover the nuanced interactions with AI companions.
No regulations are yet explicitly designed to handle the ethical complexities of AI-mediated relationships.
There’s a lack of clear guidelines on how data collected through intimate conversations can be used, especially when it comes to emotional manipulation or targeted advertising based on vulnerabilities.
What Needs to Be Done?
* Policy Development: Expand regulations to address the unique challenges AI companions pose, such as clear guidelines on data usage, consent, and ethical AI design.
* Ethical Standards: Industry-wide ethical standards should be established to ensure companies prioritize user well-being over profit.
* Transparency: Companies must provide users with clear options to control their information.
* Public Awareness: Users should be educated about the potential risks of sharing personal information with AI companions.
Final Thoughts- The Convenience of Addressing Symptoms
It’s always easier to tackle the symptoms rather than address the root causes.
Feeling lonely? There’s an app for that. Problem solved, right?
But is it really?
AI companions offer that instant emotional support we crave. In a world obsessed with quick fixes and immediate gratification, it’s no wonder we’re drawn to solutions requiring minimal effort and promising maximum comfort.
But by leaning on AI for companionship, are we sidestepping the harder, more meaningful work of building bonds with fellow humans?
* How much do we really know about our brain (or even a rat’s brain)?
* What’s the deal with current efforts to build human-like AI versus alien-like AI?
In the end, we can discuss where all this might be heading.
From Mimicking Birds To Developing Airplanes
It’s the early 1900s, and everyone’s obsessed with birds. Naturally, early inventors thought, “If birds can fly, why can’t we?” So, they tried to build machines with flapping wings.
Spoiler alert: It didn’t quite work out.
Leonardo da Vinci’s Ornithopter Design (1485)
da Vinci’s sketches of the Ornithopter, a machine designed to mimic the flapping of bird wings, are some of the earliest documented attempts to design a flying machine.
Leonardo meticulously studied the anatomy of birds and bats, believing that humans could achieve flight by replicating their wing motion.
While the Ornithopter never left the drawing board, it laid the groundwork for future inventors to think about aerodynamics and mechanics.
Otto Lilienthal’s Gliding Experiments (1890s)
The early flying machines were more of a folly than a functional aircraft, proving that directly mimicking nature isn’t always the best approach.
Fast forward to the 1890s, and you meet Otto Lilienthal. Unlike his predecessors, most of them focused on flapping wings, Lilienthal shifted the focus to understanding lift and control.
ienthal crafted fixed-wing gliders inspired by the curvature of bird wings and made over 2,000 successful glides. His dedication provided crucial data on wing shape and aerodynamic principles, directly influencing the Wright brothers’ breakthrough.
Lilienthal’s experiments showed that instead of merely imitating birds, understanding the fundamental principles of flight — like lift and control — was key.
Some Inspiration from Nature, Plus A Lot Of Physics Understanding
These later inventors, like the Wright brothers, zeroed in more on stuff like aerodynamics, control surfaces, and engines to finally crack the code of powered, controlled flight.
People didn’t just build planes out of thin air — they studied birds, tried to replicate their flight, and ended up with a lot of failed contraptions. It cost quite a few broken legs or, in some cases, the inventors’ lives. But those attempts weren’t pointless. They were part of the process.
They showed us what didn’t work, which was just as crucial as figuring out what did.
You probably started to see a pattern — a tendency to look at nature and think, “If it works for them, maybe it can work for us.”
These ideas inspired by nature generally do not lead to immediate success, but they are necessary stepping stones to progress.
Could AI be following a similar path?
How Much We Know About Birds vs. Our Brain
Top-Down Understanding of How Birds Fly
Think of our knowledge of bird flight as having a master blueprint.
We’ve figured out the big picture — the key physics rules that explain how things soar through the air: lift, drag, thrust. It’s like we’ve cracked the code of flight, and now we can use it to improve jets or to design drones.
Bottom-Up Approach to Understanding the Brain
Now, when it comes to the brain, it’s a whole different ball game.
We know a bunch about how individual brain cells chat with each other — passing electronics and sending chemical messages. The bottom-up approach.
However, the major challenge is piecing together how these billions of neurons interact to create complex thoughts, emotions, consciousness, and behaviors.
Unlike aerodynamics, no comprehensive theory can predict how changes at the neuronal level translate into changes in cognition or behavior.
Why This Distinction Matters
* Predictability and Control: In aerodynamics, the top-down understanding allows for precise control and predictable outcomes. In neuroscience, the bottom-up approach means we can only observe and manipulate individual cells but struggle to predict the brain’s overall behavior.
* Application of Knowledge: Our top-down knowledge in aerodynamics has led to aviation and aerospace. In contrast, the bottom-up knowledge of the brain hasn’t yet culminated in a complete understanding necessary to replicate human cognition in AI.
What Have We Achieved by Mimicking the Brain (Cells)?
Let’s chat about what we’ve achieved so far by trying to copy the brain and whether we can go even further — or if it’s time to try something different. Just so you know, a lot of concepts I cover here are going to be massively simplified.
Neural Networks, Deep Learning, and Advancements in Cognitive Tasks
One of the big things we’ve done is create neural networks, which are computer models inspired by the brain’s network of neurons.
Deep learning is a subset of machine learning that uses these neural networks with many layers (hence “deep”) to process data in complex ways.
By using neural networks and deep learning, AI systems can learn from data, recognize patterns, and make decisions — kind of like how our brains work. This technology is behind many of the AI applications we use today.
Examples of what we’ve achieved with neural networks:
* Facial and Speech Recognition: Your smartphone can recognize your face to unlock the screen or understand your voice commands.
* Language Translation: Apps like Google Translate can understand and translate languages.
* Game Mastery: like AlphaGo, have defeated human champions in complex games like Go and Chess.
* Or your favorite, large language models (LLMs) like GPT: Models under ChatGPT are trained on massive datasets of text from the Internet.
By mimicking certain aspects of how our brain cells communicate with each other, we’ve enabled AI to perform tasks that used to require human intelligence. It’s pretty impressive when you think about it!
Can Mimicking the Brain Get Us Further?
There’s a good chance we can still learn a lot by studying the brain. Scientists are exploring areas like:
* Neuromorphic Computing: This is about designing computer hardware that works more like the brain, which could make AI systems faster and more efficient.
* Understanding Consciousness: If we can figure out how consciousness works, maybe we can create AI that’s more aware and adaptable.
But here’s the thing: the brain is super complex, and we don’t fully understand it yet. So, relying solely on mimicking it might limit us.
The Possibility of Alien Intelligence
What if machine intelligence could develop in ways that are fundamentally different from our own cognition?
Imagine AI that processes information in ways we can’t even comprehend yet. It might sound like something out of a sci-fi, but considering this possibility opens up exciting avenues.
Join me and think about it: machines optimized for silicon-based hardware could handle asks faster and more efficiently than if they were designed to mimic our carbon-based brain cells. These types of AI could develop novel capabilities beyond human comprehension, tackling problems in ways we haven’t even imagined.
Challenges in Conceptualizing Non-Human Intelligence
Here’s the kicker: our brains (like rats, dogs, and humans) are the only examples we have of intelligence.
It’s tough to imagine something truly alien because we naturally project our own experiences and thought patterns onto the technology we create.
This anthropocentric bias limits our ability to explore radically different forms of machine cognition. It’s like trying to describe an entirely new cuisine if you only know fish and chips or beans on toast. Sorry, no offense.
Not to mention the potential communication barrier — how do you talk to an AI that doesn’t think like you?
Saying that, researchers are already looking into this. Examples like:
* Evolutionary Algorithms: These let AI evolve over time through processes similar to natural selection. The idea is to let the AI “discover” solutions we might not think of.
* Swarm Intelligence: Inspired by how groups of animals like bees or ants work together, this approach lets simple agents cooperate to solve complex problems.
The Future of AI: Human-Like or Alien?
Scenario 1 — AI Becoming More Human-Like:
If we keep focusing on mimicking human cognition, we might develop AI that thinks and reasons much like we do. This could make AI more relatable and better at understanding human emotions, language nuances, and social cues. Imagine an AI that follows commands and understands sarcasm or tells you more dad jokes than your dad could!
However, we still don’t fully grasp how consciousness arises, how memories are formed and recalled, or how our emotions influence decision-making.
Without this understanding, creating AI that truly mirrors human thought processes remains a significant challenge.
Scenario 2 — AI Becoming More Alien:
On the flip side, pursuing unique forms of machine intelligence could lead to breakthroughs we can’t even imagine yet. For instance, AI combines with quantum computing principles or bio-inspired algorithms that don’t have a direct human equivalent.
Here’s a catch.
If AI develops intelligence that is entirely different from ours, communication might become a challenge. How do we understand or trust decisions made by an AI that thinks in ways we can’t comprehend? We don’t even know whether to trust AI built inspired by how our brain works!
Scenario 3 — A Hybrid Approach:
Perhaps the most likely and practical approach.
Just as airplanes aren’t exact replicas of birds but incorporate principles of flight, future AI systems might blend human-inspired models with novel computational methods.
An example of this hybrid approach is Neural-Symbolic AI combined with machine learning. Neural-Symbolic AI uses rules and logic (like human reasoning), plus machine learning to find patterns in data without explicit instructions. Together, they can create systems that are both interpretable and powerful.
Wrapping It Up + Coming Up Next:
So, the next time your friend or curious kid asks why we’re trying to mimic the human brain in AI, you’ll have plenty to share!
Some other questions I’ve been pondering that I want to share with you!
Have you ever thought about how our memory works compared to AI? I might be exploring the topic — “Remember That Time? How You Remember vs. How AI Remembers.” Or what about how decisions are made — “Gut Feeling or Calculated Risk? Decision-Making in Brains and Bots.”
If you have also asked the same questions or are interested in similar topics, subscribe to me so you don’t miss any fun AI/ technology insight!
Back in the 1890s, very few people had one. People were still getting around with horses, and while cars seemed exciting, they weren’t something most people could easily use. They were expensive and explosive (yes, you heard it right), and roads were still made for carriages or your legs.
The first-ever organized car race, held in 1894, was more about reliability and endurance than outright speed. The primary challenge was not which car ran faster but whether these vehicles could even finish the race.
The idea of an “auto-mobile” was great, but the technology wasn’t ready yet. This is where technology maturity comes in. The tech (roads, engines, gas stations) needed time to catch up before cars became part of everyday life.
Today, most families in developed countries can afford a car, and we don't have to worry that it breaks down every mile. So we all want and can’t even live w/o one. This is product-market fit. The market (people like you and me) and the product (the car) are in sync.
So, just like with early cars, AI is still in the phase where the idea is exciting, but the tech isn’t quite there yet. Yes, we have ChatGPT, Copilot, and AI writers… but tell me, when was the last time you copy-paste and then done? That’s because the technology maturity isn’t fully developed. We’re in the “at least get to the finish line car race” phase of AI — where the idea is groundbreaking, but the execution still has a way to go.
Let me show you how historical technologies like electricity and the steam engine went through a similar journey — from novelty to necessity — only after years of technological improvements. And that’s where AI is headed… but it’s not quite there yet.
Some of you know how much I love adding mini-games to my articles. Here’s a technology maturity vs. product market fit flip card game:
It Can Take Centuries From Tech Maturity To Product-Market Fit
Just like AI today, many of the technologies you and I now take for granted didn’t start as everyday essentials.
They needed time — sometimes decades or even centuries — to develop the necessary infrastructure and improvements before they could really take off.
Electricity: From Discovery to Powering Your Light Bulb
Electricity was discovered in the 1700s.
But at first, it was nowhere near being useful.
It wasn’t until the 1800s that things really started to click.
By the 1870s, Thomas Edison had invented the incandescent light bulb. But Edison’s bright idea came with a catch. His system used Direct Current (DC), which worked fine for short distances but failed in long-distance transport. Enter Nikola Tesla, who proposed Alternating Current (AC) as the solution. Yet, Edison famously resisted, saying:
Fooling around with alternating current’s just a waste of time. Nobody’ll ever use it. Too dangerous!
Well, as you might have guessed, AC won the war. With other inventions/improvements, like replacing carbon with a tungsten filament, incandescence finally became more efficient than gas or kerosene-powered light. Hence, reached the product-market fit.
Automobiles: Early Challenges and Breakthroughs
The first steam engine was invented in the 1710s. Yes, it is the first engine-powered vehicle to appear after 50 years. But it looks like this, and it is slower than your average walking speed.
It wasn’t until another 150 years later that the first wave of automobile entrepreneurs started producing workable cars.
Did you know there was a point in history when there were more electric engines than combustion engines?
By the 1890s, about 38% of automobiles were electric, only 22% were powered by internal combustion engines, and the rest were still running on steam. Of course, there weren’t that many automobiles to start with.
Between steam, electricity, and gasoline (internal combustion), each power source had its moment and presented its challenges.
* Steam engines had great power but were impractical for everyday use. Imagine starting a car that takes 45 minutes; bring liters of water to refill every 20 to 30 miles.
* Electric cars were quiet and clean, perfect for urban areas. But here’s the catch: the 1890s electric cars could only go 30 miles before needing a recharge. And charging stations? You get carriage stables.
* The internal combustion engine brought speed and longer range. But! Early models had to be manually cranked to start — you could also get seriously injured if the crank kicked back.
The turning point came with the famous Ford Model T, and the development of the assembly line drastically lowered production costs. By 1929, 60% of American families owned a car.
The car as a product finally found its product-market fit, but it took time for the technology (engine design, mass production, road networks) AND the production process to mature enough for cars to be part of our daily lives.
Meanwhile, the electric engine — once a dominant force — has only recently slowly made its way back.
The Refrigerator: From Luxury to Kitchen Staple
The idea of refrigeration goes back thousands of years. In ancient Mesopotamia, people built ice houses to store food;in ancient China, about 200 B.C., they built ice cellars.
These early methods were ingenious but relied on ice and snow, limiting their practicality.
Fast forward to the 1750s, a Scottish professor made a breakthrough, using a vacuum pump and ether to absorb heat and cool the air. It was not for another 150 years that General Electric introduced one of the first household gas-powered refrigerators in the 1910s.
The turning point came in the 1930s when safer synthetic refrigerants like Freon were developed. This made refrigerators smaller, cheaper, and more reliable.
When the refrigerator finally achieved product-market fit, it became a must-have in almost every kitchen.
Connecting the Dots with AI
What do all these examples have in common?
They all had the potential to change the world, but it took years — even centuries — of refinement before they became things the general population couldn’t live without.
That’s where AI is right now. It has the big idea — just like the early days of electricity, cars, and fridges — but the technology isn’t quite ready for seamless, everyday use.
We’re still in that in-between phase where the idea is exciting, but the tech needs to catch up. And until it does, AI can’t truly hit that product-market fit.
Current State of AI
Visible Integration
Unlike flipping on a light switch, using AI often reminds you that you’re dealing with a work in progress.
Take AI writing assistants, for example. They can churn out paragraphs of text, but very often— rambling, off-topic, or just not quite hitting the mark. You find yourself playing editor-in-chief, tweaking and correcting, wondering if it might’ve been quicker to write it yourself.
Then there’s the rush of companies eager to slap “AI-powered” onto their products because it’s the buzzword of the decade.
Varied Maturity Levels Across Different Industries
AI shines in specific, well-defined tasks, but its maturity varies across industries. Let’s dive into a few:
* Healthcare: AI is getting really good at analyzing medical images. For instance, it can sift through thousands of X-rays and MRIs to detect anomalies like tumors or fractures. In one case, an AI could identify skin cancer as accurately as dermatologists. However, it can not yet consider a patient’s full history, symptoms, and those subtle cues a doctor picks up during an exam.
* Genome sequencing: In genomics, AI helps analyze vast genetic data. It can identify patterns and potential genetic markers for diseases faster than any human could. Companies like Deep Genomics use AI to predict the impact of genetic mutations, accelerating research in personalized medicine. Yet, genes don’t tell the whole story without context. Lifestyle or interactions between genes and the rest of your body add to the complexity that AI doesn’t fully grasp.
Indicators Beyond Adoption Rates
It is not about how many people use it but how well it works.
Some key indicators might help you decide whether an AI application is genuinely mature.
Usability and Reliability
A mature AI delivers a smooth user experience. Think about voice assistants like Siri, Alexa, or Gemini. They’re handy — you can ask about the weather, set reminders, or play your favorite song. But how often have you repeated commands because it didn’t understand you?
A mature AI should be intuitive and dependable, not a source of daily annoyance.
Consistency and Accuracy
A mature AI delivers consistent and accurate results. Take facial recognition technology, for example. It’s used in everything from unlocking phones to airport security. Yet, it has shown significant biases and inaccuracies, especially with different ethnicities and ages.
When an AI doesn’t reliably perform across the board, it highlights that the technology isn’t fully baked yet.
Trust Worthy
A mature AI is when you can trust its judgment. Again, with the healthcare example, AI can be used to predict patient outcomes or recommend treatments. Sounds fantastic, but doctors often need to double-check AI’s suggestions because they’re not always correct.
Would you trust an AI to make critical decisions about your health without a human in the loop?
My Take + Until Next Time…
Don’t get me wrong, AI 100% holds immense promise.
Its current state of maturity prevents most applications from achieving true product-market fit. Just as electricity requires the right infrastructure and understanding to become indispensable, AI must overcome its own set of challenges—reliability, usability, and trustworthiness—to fully integrate into our daily lives.
To delve deeper into how historical tech cycles mirror the current AI hype, check out my previous article, “I Studied 200 Years’ Of Tech Cycles. This Is How They Relate To AI Hype.” Understanding these patterns will not only help ground your expectations but also help you navigate the future of AI with informed skepticism and optimism.
Subscribe for free to receive new posts and support my work.
I know what I promised last time. I’m still working on the idea of a link between AI and neuroscience. A lot of ideas that I want to share with you.
Discover shows related to 2nd Order Thinkers., based on actual content similarities. Explore podcasts with similar topics, themes, and formats, backed by real data.
