I Asked ChatGPT To Come Clean on the Limits of AI: Here is their Reply
Color me a hardened cynic of the hyped-up potential for Artificial Intelligence (AI) to shape a wiser, better-informed future for humanity. But, like other inquisitive souls, I put ChatGPT to the test to see how AI ‘sees’ itself in this discussion.
I asked ChatGPT the following:
Skeptics of artificial intelligence argue that machine intelligence will never match human brain power for wisdom and creative thought because AI is merely an aggregation of machine code algorithms limited by the capacity of the human programmers with their systemic bias and limitations. What evidence supports or contradicts this assertion?
ChatGPT said:
This assertion—that AI will never match human brain power for wisdom and creative thought due to its basis in algorithmic code and human limitations—touches on deep philosophical, technical, and empirical questions. Let’s break down the evidence both supporting and contradicting this claim:
✅ Evidence Supporting the Skeptics’ View
-
AI is limited by human-designed algorithms
-
Argument: AI systems are programmed by humans, who inevitably encode their biases, assumptions, and limitations into the design and training data.
-
Example: Bias in large language models has been well-documented (e.g., racial/gender bias in outputs), reflecting societal and systemic imbalances in their training data.
-
-
Lack of consciousness and intentionality
-
Argument: AI lacks qualia, subjective experience, or consciousness, which are often seen as essential to true wisdom or deep creative insight.
-
Example: While AI can generate art, poetry, or philosophical musings, it doesn’t experience meaning—it simulates rather than originates.
-
-
Narrow generalization
-
Argument: AI often excels in narrow tasks but lacks general reasoning and adaptive learning across disparate domains like humans do.
-
Example: GPT-4 or image generators can produce stunning results, but they don’t understand the world; their “knowledge” is statistical rather than conceptual.
-
-
Absence of moral or ethical grounding
-
Argument: Wisdom is not just intelligence but involves judgment, ethical reflection, and empathy—traits that AI cannot genuinely possess.
-
Example: AI might suggest efficient but ethically questionable solutions, like maximizing profits at the cost of human wellbeing, if not constrained.
-
🔁 Evidence Contradicting the Skeptics’ View
-
Emergent creativity and problem-solving
-
Counterpoint: AI has demonstrated unexpected creativity and insight—sometimes producing outputs that surprise even its creators.
-
Example: AlphaGo’s move 37 in its match against Lee Sedol was described as creative and “godlike,” not predicted by any human strategy.
-
-
Self-improving systems and reinforcement learning
-
Counterpoint: AI systems can self-optimize and explore beyond explicit human programming via reinforcement learning or evolutionary algorithms.
-
Example: OpenAI’s models refine performance via RLHF (Reinforcement Learning from Human Feedback), incorporating complex value preferences.
-
-
Expanding cognitive limits
-
Counterpoint: AI can process, synthesize, and “understand” data at scales and speeds impossible for humans, offering new forms of insight.
-
Example: AI systems assist in discovering new drug compounds or proving mathematical conjectures that were beyond human reach.
-
-
Collaboration with human creativity
-
Counterpoint: AI enhances human creativity, acting as a cognitive amplifier rather than a simple tool.
-
Example: Artists, composers, and writers are increasingly collaborating with AI to create novel works, from literature to film to fashion.
-
🧠 Philosophical Considerations
-
Wisdom vs. Intelligence: Wisdom involves context, emotion, ethical reasoning, and lived experience. It is unclear whether AI can ever truly possess wisdom without consciousness.
-
Creativity Defined: If creativity is defined as novel and valuable combinations of existing ideas, AI already achieves this. But if it requires intent, emotion, or existential motivation, current AI falls short.
🔍 Conclusion
The assertion that AI will never match the human brain in wisdom and creative thought is partially supported by current evidence—particularly in terms of consciousness, ethical grounding, and subjective experience. However, technological progress increasingly challenges these boundaries, with AI demonstrating surprising levels of creativity, pattern recognition, and adaptive learning.
Ultimately, whether AI can match or exceed human creativity and wisdom may hinge on how we define these concepts—and whether machines can ever truly think or feel, rather than simulate.
About John O’Sullivan : John is CEO and co-founder (with Dr Tim Ball) of Principia Scientific International (PSI). He is a seasoned science writer and legal analyst who assisted skeptic climatologist Dr Ball in defeating UN climate expert, Michael ‘hockey stick’ Mann in the multi-million-dollar ‘science trial of the century‘. From 2010 O’Sullivan led the original ‘Slayers’ group of scientists who complied the book ‘Slaying the Sky Dragon: Death of the Greenhouse Gas Theory’ debunking alarmist lies about carbon dioxide plus their follow-up climate book. His most recent publication, ‘Slaying the Virus and Vaccine Dragon’ broadens PSI’s critiques of mainstream medical group think and junk science.
Please Donate Below To Support Our Ongoing Work To Defend The Scientific Method
PRINCIPIA SCIENTIFIC INTERNATIONAL, legally registered in the UK as a company incorporated for charitable purposes. Head Office: 27 Old Gloucester Street, London WC1N 3AX.
Trackback from your site.
Howdy
| #
‘Insight’ is not computer parlance, neither is consciousness.
AI cannot think out of the box regardless of how easily people are impressed with it’s capabilities.. As long as it is computer generated, it is at best, emulation. A knock off.
Reply
VOWG
| #
Programing, yesterday, today and tomorrow.
Reply
Tom
| #
A/i retards will make excellent mechanical geniuses and supreme digital prison wardens. That is their true purpose as in controlling all variables of human life so that it can be murdered. You’ll see. If A/i was here to save and improve the human condition, there would be no more wars, deadly mRNA poisons, deadly drugs, poison food, skytrails, 5G, and other toxicity all chipping away at the life of humans. So which is it? Life for the arrogant tech snobs and death for the rest of us.
Reply
Jerry Krause
| #
Hi John O’Sullivan,
In 1968 I wrote a 99 step code of a mainframe computer to analyze the diffusion data I had spent two years collecting for my PhD thesis research. So I know that a computer only does, what it is told by a person, to do. In your articles title “I Asked ChatGPT To Come Clean On The Limits Of AI: Here Is Their Reply” you acknowledge this for you wrote ‘Their Reply” and not ‘Its Reply’.
Ask ChatGPT to give you its reply in German and you might discover that the SMART (intelligent) computer only speaks English.
Have a good day
Reply
Howdy
| #
Do computers speak at all? If I create a tone from my mouth, then use my hands as an envelope shaper to create a recognizable sound, am I still speaking, or emulating?
Reply
John O'Sullivan
| #
Jerry, Interesting idea. I will try. Hope others will also put AI to the test and help work out the limits of the technology
Reply
Howdy
| #
https://medium.com/@pagany/the-question-that-stumped-chatgpt-for-5-whole-minutes-c387710ee496
https://www.zdnet.com/article/6-things-chatgpt-cant-do-and-another-20-it-refuses-to-do/
Reply
Howdy
| #
I asked AI what it is not. The answers are pretty much as explained previously:
https://iask.ai/q/what-is-AI-not-n6677fo
Notice it took the question literally, and didn’t ask if I was inquiring what “AI not” is just to be sure.
Reply