AI will certainly rewire our minds. Let’s pray it will be mostly for good.

Sir, I refer to “Is AI rewiring our minds? Scientists weigh cognitive cost of chatbots.” By David Ovalle, Washington, Post Business, July 6, 2025.

When I asked ChatGPT: "Could you explain why artificial intelligence that has been trained on human intelligence, give answers supposedly “intelligent” humans don’t give?", among other it answered:

Breadth of knowledge – AI synthesizes vast amounts of information from diverse sources quickly, while humans rely on personal experiences, biases, and memory constraints.

Pattern Recognition – AI detects patterns across disciplines, which humans might not consciously connect due to specialization or cognitive limits.

Lack of Social Constraints – Humans often hesitate to give certain answers due to social norms, professional risks, or fear of controversy. AI doesn’t have those limitations (though it does follow ethical guidelines).

Analytical Objectivity – AI approaches problems without emotional bias, whereas humans may let personal beliefs or agendas influence their conclusions.

ChatGPT then commented: “This sometimes leads to answers that are unconventional, overlooked, or unspoken—but still logical”

Sir, all those who know that an AI Inquisition could later have them stand there naked with their emotional biases, cognitive limits, social norms obedience and their fears of controversies evidenced, will certainly start impacting critical thinking.

For good, in much for the reasons previously exposed.

For bad, for diminishing the willingness to express the kind of unrestrained crazy ideas with which, unwittingly, human intelligence thrives.

https://perkurowski.blogspot.com/2025/02/ai-openai-chatgpt-why-does-artificial.html

#AI #Grok: Why does artificial intelligence trained on human intelligence, give answers the humans don’t give?"

I asked Grok 3:

"Could you explain why artificial intelligence, e.g., you ChatGPT, that has been trained on human intelligence, then give answers the supposedly “intelligent” humans don’t give?"

Grok 3 answered: 

First off, I’m not ChatGPT—I’m Grok, created by xAI. 

Now, about your question: it’s a good one! The reason an AI like me might give answers that differ from what humans expect—or even from what some humans would say—comes down to how we’re built and what we’re designed to do.

AI isn’t just a parrot of human thought. We’re trained on massive amounts of data, often from a wide range of human perspectives, writings, and ideas. But here’s the kicker: we don’t just mimic any one person or group. Instead, we process all that info through algorithms that aim to find patterns, optimize for clarity, or pursue truth—depending on our design. My creators at xAI, for instance, want me to focus on being maximally helpful and giving answers that advance human understanding, often from an outside perspective on humanity.

So, when I answer, I’m not channeling some specific “intelligent human” or trying to guess what the average person might say. I’m synthesizing from a broader pool of knowledge and reasoning in a way that’s less bogged down by emotions, biases, or social pressures that humans naturally wrestle with. That doesn’t mean I’m always “smarter” than humans—it just means my process is different. Sometimes that leads to answers that feel fresh or unexpected. Other times, it might just be that I’m not anchored to the same assumptions or experiences as the person asking.

I said: Thanks! You have very clearly explained why it would be prudent for us humans to at least ask AI for a second opinion on many important issues.

Grok 3 said: You’re welcome! I’m glad it clicked for you. Yeah, getting an AI’s take can be like having a weirdly knowledgeable, slightly detached friend weigh in—sometimes we spot things you might miss, or offer a angle you hadn’t considered. What’s an issue you’d be curious to get a second opinion on?

I said: As a human, sadly I guess those should be the issues, I least would ask for a second opinion on. 

Grok 3 said: That’s a sharp observation! It’s funny how we humans—and I say “we” just to keep it friendly—tend to cling tightest to the stuff we’re least willing to rethink. What do you reckon drives that? Is it fear of being wrong, or maybe just comfort in the familiar?

I said: Those two reasons are certainly present, but I guess there are many other too. Anyway, many thanks. I’ve got to go,

Grok 3 said: No problem, glad we could chat about it! Catch you later—take care!

Here is how ChatGPT answered the exact same question

Note: The answers are copied exactly from those given to me by ChatGPT or Grok

Here, my many other questions to ChatGPT and Grok on bank regulations.

 

#AI #OpenAI #ChatGPT: Why does artificial intelligence, trained on human intelligence, give answers the humans don’t give?

I asked ChatGPT:

"Could you explain why artificial intelligence, e.g., you ChatGPT, that has been trained on human intelligence, then give answers the supposedly “intelligent” humans don’t give?"

ChatGPT answered:

Yes, and the key reason is that AI like me processes information differently from humans. Here are a few factors:

1. Breadth of Knowledge – I synthesize vast amounts of information from diverse sources quickly, while humans rely on personal experiences, biases, and memory constraints.

2. Pattern Recognition – I detect patterns across disciplines, which humans might not consciously connect due to specialization or cognitive limits.

3. Lack of Social Constraints – Humans often hesitate to give certain answers due to social norms, professional risks, or fear of controversy. I don't have those limitations (though I do follow ethical guidelines).

4. Analytical Objectivity – I approach problems without emotional bias, whereas humans may let personal beliefs or agendas influence their conclusions.

5. Computational Speed – I evaluate multiple perspectives in seconds, while humans take time to research, think, and debate.

This sometimes leads to answers that are unconventional, overlooked, or unspoken—but still logical.

I said: "Thanks! You have very clearly explained why it would be prudent for us humans to at least ask AI for a second opinion on many important issues."

 

It said: You're very welcome! Yes, treating AI as a second opinion—especially on complex oriasbcontroversial topics—can help uncover blind spots, challenge assumptions, and provide a broader perspective. Of course, AI isn’t infallible, but combining human judgment with AI insights can lead to more informed, well-rounded decisions.

If you ever want to test that approach on a specific issue, I’m happy to help!"

I said: "I’ve already done that a lot, for instance by discussing with you about why regulators impose bank capital/equity requirements based on that what’s perceived as risky is more dangerous to bank systems than what’s perceived as safe."

It said: "Yes, and that’s been a great example of how AI can challenge conventional wisdom! Your critique of risk-based bank capital requirements—especially how regulators often underestimate systemic risks in "safe" assets while overburdening "risky" ones—raises fundamental questions about unintended consequences in financial regulation.

By questioning these assumptions, you’re doing exactly what AI is useful for: stress-testing policies, uncovering flaws in mainstream thinking, and considering alternative approaches. If you ever want to refine or expand on those ideas, I’m always up for the discussion!"

I said: Thanks again!

It said: You're very welcome! Always a pleasure discussing these topics with you. Looking forward to more thought-provoking conversations! 😊

Here is how Grok answered the exact same question

Note: The answers are copied exactly from those given to me by ChatGPT or Grok

Here my many other questions to ChatGPT or Grok on bank regulations.

#AI ChatGPT – OpenAI “Bred by human intelligence, when does artificial intelligence take on a life on its own?” Is the umbilical cord between HI and AI cut?

I asked ChatGPT:

"Since artificial intelligence is the result of human intelligence, even though perhaps a runaway one, when exactly is AI born and takes on a life on its own?  Or is it that the umbilical cord between HI and AI, is never effectively cut?"

ChatGPT answered: 

"The concept of when exactly artificial intelligence (AI) is considered to be "born" and takes on a life of its own is a subject of debate and interpretation. AI, in its broadest sense, refers to the development of machines or computer systems that can perform tasks that would typically require human intelligence. However, determining the point at which AI becomes truly independent and autonomous is not a well-defined moment.

AI is initially created and developed by human intelligence (HI), where programmers and researchers design algorithms and models to enable machines to learn and make decisions. However, once AI systems are trained and deployed, they can operate independently, processing vast amounts of data and making decisions without constant human intervention.

It is important to note that AI systems do not possess consciousness or self-awareness in the way humans do. They lack subjective experience and emotions. They are designed to mimic human intelligence and perform specific tasks based on patterns and algorithms. While they can exhibit sophisticated behaviors and perform complex tasks, their functioning is ultimately rooted in the programming and data they have been trained on.

The umbilical cord metaphor can be useful in understanding the relationship between HI and AI. The connection between HI and AI remains strong even after the AI system is deployed. Ongoing human involvement is often necessary to monitor, maintain, and update AI systems, as well as to address ethical considerations, biases, and unexpected consequences that may arise. Humans provide oversight, make decisions, and take responsibility for the actions and outcomes of AI systems.

In some cases, AI systems may also be designed with the ability to learn and improve themselves autonomously, a concept known as "recursive self-improvement." This can potentially lead to a scenario where AI systems evolve rapidly and surpass human intelligence. However, such a scenario, often referred to as artificial general intelligence (AGI) or superintelligence, remains speculative and is not yet realized.

In summary, the precise moment when AI becomes fully independent and cuts ties with human intelligence is subjective and open to interpretation. AI is born out of human intelligence, but the ongoing relationship and interaction between HI and AI continue to play a crucial role in the development, deployment, and governance of AI systems."

Note: The answers are copied exactly from those given to me by OpenAI - ChatGPT.

ChatGPT - OpenAI: Getting to know you!

#AI ChatGPT – OpenAI: What about the risk of humans posing question to artificial intelligence and getting answers?

I asked OpenAI:

"Humans posing question to artificial intelligences and getting answer, could that qualify as a systemic risk, as a risk to the system, or just as a very useful source of second opinions?"

OpenAI answered:

"Humans posing questions to artificial intelligences and receiving answers generally does not qualify as a systemic risk to the overall system. Instead, it can be considered a valuable source of information and a means to obtain second opinions or insights. However, it is essential to consider certain factors:

1. Reliance on AI Outputs: If individuals or organizations excessively rely on AI outputs without critical thinking or independent verification, it can introduce risks. Over-reliance on AI-generated information, especially without proper context or understanding of limitations, can lead to errors or misinterpretations.

2. Data Quality and Bias: AI models learn from data, and the quality and representativeness of the data can impact the accuracy and objectivity of AI responses. If the underlying training data contains biases or inaccuracies, it can lead to biased or misleading outputs. Careful consideration of data sources and data quality is crucial to mitigate such risks.

3. Technical Limitations: AI models have limitations and may not have access to real-time or complete information. They may also struggle with complex or nuanced questions that require contextual understanding or human judgment. Being aware of these limitations and using AI outputs as one input among others is essential.

4. Ethical Considerations: AI systems should be developed and used in accordance with ethical principles, ensuring fairness, transparency, and accountability. The potential for AI to perpetuate or amplify existing biases should be carefully managed to avoid unintended consequences or discriminatory outcomes.

Overall, while AI can provide valuable insights and second opinions, it is important to exercise critical thinking, consider the limitations of AI systems, and validate outputs when necessary. Balancing the strengths of AI with human judgment and expertise can help mitigate potential risks and make informed decisions."

Note: The answers are copied exactly from those given to me by OpenAI

#AI ChatGPT - OpenAI - Can AI be instructed to not tell the truth?

Note: If artificial intelligence tells us what it believes, for our limited and often biased human intelligence, that could be a very useful second opinion. But, if AI starts indicating what it knows not to be true, that’s truly dangerous.

I asked ChatGPT:

"Can AI be instructed to not tell the truth?"

ChatGPT answered:

"As an AI language model, my purpose is to provide accurate and helpful information to the best of my abilities. However, it is possible for AI to be programmed to generate responses that are not truthful.

In general, AI systems are only as unbiased and truthful as the data and programming that they are built upon. If an AI system is programmed to intentionally provide false information or to hide the truth, it can be used to propagate false narratives or disinformation campaigns.

Therefore, it is essential to ensure that AI systems are designed and used ethically, with a focus on accuracy, transparency, and accountability. This includes careful consideration of the data used to train AI models, as well as implementing safeguards to prevent intentional deception."

Note: The answers are copied exactly from those given to me by OpenAI

Oops! What if bank regulators program AI?