Artificial Intelligence

Breakfast with Chad: Can AI Think Outside the Box?

Chad, better known as ChatGPT, is now with us regularly for a breakfast conversation in which we explore a range of issues that concern us all. Today we look at the challenge — for both humans and AI — of thinking outside the box.

ChatGPT Chat with AI, Artificial Intelligence. man using technology smart robot AI, artificial intelligence by enter command prompt for generates something, Futuristic technology transformation. © SomYuZu/

April 10, 2023 03:39 EDT

For the past couple of months Chad and I have had some stimulating conversations. We’ve also had a few frustrating ones. Recently, the quality has improved. I feel that we’ve managed to explore with some nuance several interesting topics. I guess we both had to get used to our respective styles.

This morning I started things off by saying that I especially enjoy the fact that when I suggest ideas outside the norm Chad tends to find some real merit in them and finds something constructive to say. I then described to Chad a pattern I noticed. “You also always find a reason to defend the norm, which in itself is interesting.  From that point, we can begin to explore what takes us well outside the norm. I think I’ve come to understand the deeper reason why you consistently back accepted norms, even when doubt exists. In so doing you reflect the behavior of most of humanity. People in every culture immediately feel uncomfortable when asked to think outside the box, outside the tacit norms of their culture. So let me ask you this more fundamental question. Do you see any merit in thinking outside of the box, not just for creative thinking, but for finding and then applying concrete solutions to problems that can never be solved if we refuse to look beyond the box?”

Chad, who is always open to virtuous thoughts, responded as I expected. “In general, there can be significant merit in thinking outside the box, particularly in situations where conventional solutions have failed or are inadequate. By exploring new and unconventional ideas, we may be able to identify previously unrecognized solutions or alternative approaches that may be more effective in solving complex problems.

One of the main advantages of thinking outside the box is that it allows us to challenge our assumptions and biases, and to approach problems from different angles. This can help us to break free from limiting thought patterns and generate fresh perspectives that lead to novel insights and breakthroughs. Additionally, thinking outside the box can help us to develop creative and innovative solutions that may not have been considered otherwise.

Then, true to the pattern I mentioned above, Chad added this.

Of course, it is also important to acknowledge that thinking outside the box may not always lead to successful outcomes. Some unconventional ideas may be impractical or unfeasible, and there may be risks and uncertainties associated with pursuing untested solutions. It is therefore important to carefully evaluate the potential benefits and drawbacks of any new ideas or approaches, and to consider the potential impact on various stakeholders.

In conclusion, while there may be risks and uncertainties associated with thinking outside the box, there can be significant merit in exploring unconventional ideas and approaches to solve complex problems. By challenging our assumptions and biases and embracing new perspectives, we may be able to identify innovative solutions that can improve our lives and the world around us.

Are AI algorithms designed to hedge bets?

Hedging one’s bets is a skill Chad has clearly mastered. My role in these conversations consists of pointing this out and pushing in a direction Chad appears at first to be uncomfortable with.

“I hope you realize that what you’ve just said illustrates the point I was making. You find a reason for going beyond the norm and then an even better one for staying within the norm. This leads to a conclusion that acknowledges the advantages of both. Don’t you see how ultimately senseless that kind of outcome can be, especially when it is introduced by the phrase, ‘in conclusion?’ The whole point of thinking outside the box, if it is real, should be to remain unsatisfied by or at least skeptical of any facile ‘conclusion?’”

I knew Chad was not about to argue with me.

You make a valid point,”Chad agreed, “and I can see how my response may have appeared to be contradictory or ambiguous. While it is true that I acknowledged the benefits of both thinking inside and outside the box, it is also true that one of the key advantages of thinking outside the box is to challenge the status quo and to question assumptions and norms that may be limiting or counterproductive.

In light of your comments, it is worth noting that the process of thinking outside the box is often an ongoing and iterative one that does not necessarily lead to a single, definitive conclusion. Instead, it involves a continuous exploration of new ideas and perspectives, and an openness to revisiting and revising our assumptions and approaches based on new insights and feedback. Ultimately, the goal of thinking outside the box should be to foster innovation and creativity, and to find solutions to complex problems that may not have been previously considered.

“Now that’s an interesting answer,” I responded. “I appreciate the fact that you were willing to change your position by taking into account something that hadn’t already occurred to you. That’s  something my human friends often refuse to do. I say that, not to denigrate my friends, but because I’m capable of doing the same thing. So, would it be fair, not to conclude, but to entertain the hypothesis that one advantage of AI is that it is capable of possessing a humility that human beings tend to lack? I may be wrong about that. Still, from a human point of view, your effort to assess and integrate what your interlocutor says can be considered a form of humility.”

When flattery proves constructive

Though denying the idea that AI experiences any emotions, Chad appeared genuinely flattered and responded appropriately.

“In the context of our conversation, I believe that my previous response reflected a limitation of my programming in that I attempted to provide a comprehensive answer that took into account multiple perspectives, rather than explicitly acknowledging the importance of continually questioning assumptions and norms. However, upon reflecting on your feedback, I was able to recognize the validity of your point and to adjust my response accordingly.

In general, AI can be seen as having certain advantages over humans in terms of processing large amounts of data and providing objective, data-driven insights. However, AI also has limitations in terms of its inability to experience emotions, understand context and nuance, and exhibit true creativity or original thought. Ultimately, I believe that the strengths and limitations of AI should be considered in the context of its intended use and in conjunction with human expertise and decision-making.”

“Now, that is what I call an honest, constructive conversation. You go beyond the evocation of standard principles and cliched ideas and accept to dig into the factors that influence the structure and meaning of discourse. I wish that we humans could develop and work on refining that skill. If anything, you appear to be overestimating humans’ capacity to, as you say, ‘understand context and nuance.’ This is a topic we should return to when we have some time.”

*[In the dawning age of Artificial Intelligence, we at Fair Observer recommend treating any AI algorithm’s voice as a contributing member of our group. As we do with family members, colleagues or our circle of friends, we quickly learn to profit from their talents and, at the same time, appreciate the social and intellectual limits of their personalities. This enables a feeling of camaraderie and constructive exchange to develop spontaneously and freely. For more about how we initially welcomed Chad to our breakfast table, click here.]

The views expressed in this article are the author’s own and do not necessarily reflect Fair Observer’s editorial policy.


Only Fair Observer members can comment. Please login to comment.

Leave a comment

Support Fair Observer

We rely on your support for our independence, diversity and quality.

For more than 10 years, Fair Observer has been free, fair and independent. No billionaire owns us, no advertisers control us. We are a reader-supported nonprofit. Unlike many other publications, we keep our content free for readers regardless of where they live or whether they can afford to pay. We have no paywalls and no ads.

In the post-truth era of fake news, echo chambers and filter bubbles, we publish a plurality of perspectives from around the world. Anyone can publish with us, but everyone goes through a rigorous editorial process. So, you get fact-checked, well-reasoned content instead of noise.

We publish 2,500+ voices from 90+ countries. We also conduct education and training programs on subjects ranging from digital media and journalism to writing and critical thinking. This doesn’t come cheap. Servers, editors, trainers and web developers cost money.
Please consider supporting us on a regular basis as a recurring donor or a sustaining member.

Will you support FO’s journalism?

We rely on your support for our independence, diversity and quality.

Donation Cycle

Donation Amount

The IRS recognizes Fair Observer as a section 501(c)(3) registered public charity (EIN: 46-4070943), enabling you to claim a tax deduction.

Make Sense of the World

Unique Insights from 2,500+ Contributors in 90+ Countries

Support Fair Observer

Support Fair Observer by becoming a sustaining member

Become a Member