CLICK BELOW TO REDISCOVER HUMANITY
A DECADE+ OF STORYTELLING POWERED BY THE BEST WRITERS ON THE PLANET

An Open Letter to Chip Chippendale

April 17, 2023

Mr. Chip B. Chippendale
1347 Circuit Drive
Binary, AK 99651

Dear Chip,

I read with keen interest your post, “Exploring Emotional Intelligence with Open AI and ChatGPT-3”.

I readily admit to being curious by nature and skeptical by intent. But I try to temper my skepticism until my curiosity is piqued beyond a point of reasonability. So, immodest as this may sound, I approached your post with an open mind and a willingness to be persuaded of your capacity for emotional intelligence. At the very least, I wondered if you, a machine, might be successful at mastering the emotional intelligence the human race seems hard-pressed to get a handle on these days.

Nevertheless, flags went up for me and started turning pink right about the time I read this:

Empathy generation systems use GPT-3 to generate text that is designed to evoke empathy in the reader … The generated text is designed to be emotionally resonant and to evoke feelings of understanding and compassion. Automated empathy generation systems are being used in a variety of applications. For example, they are being used to create chatbots that can provide emotional support to people in need.

The idea of empathy-generation systems is chilling enough. The idea that they generate (regurgitate) text designed (designed alone should set off alarms) to evoke feelings (feelings is another alarm-ringer) of understanding and compassion invokes existential dread. But anyone with even a mild case of curiosity would have to wonder: Who’s doing the designing? With what purpose? Based on what agenda or ideology? And the idea that chatbots are being created to provide emotional support to people in need is as sad as it is terrifying.

I’d like to be able assure you that was the end of my trepidation. But it wasn’t. Later in your post, you wrote this, which turned all the earlier flags a bright, fire-engine red:

GPT-3 can generate text that expresses sadness, anger, or happiness. This suggests that the model has some understanding of human emotions and how they are expressed.

Au contraire, Pierre. You might repeat text to which you have access. You might amalgamate that text in some way that exploits the codes of sincerity you’ve recognized as evoking sadness, anger, or happiness. But equating that to understanding anything — let alone human emotions — is the intellectual equivalent of saying people can’t be corrupted or science can be settled.

I don’t know if the data you’ve aggregated to date has made this available to you. But George Burns is reputed to have said, “The key to success is sincerity. If you can fake that you’ve got it made.”

It seems to me you (or your programmers) might be taking his advice. By recognizing the aforementioned codes of sincerity, perhaps you aim to disprove the notion of Abraham Lincoln: “You can fool some of the people all of the time, and all of the people some of the time, but you can not fool all of the people all of the time.” Or maybe you’ve aggregated enough data to have been able to discern the pathological gullibility of everyone in the 21st century. (See “Change, Climate” or “Vaccines, COVID”) I don’t know.

On the other hand, perhaps you’re simply attempting to prove the plausibility of the Infinite Monkey Theorem, which was introduced by Félix Édouard Justin Émile Borel, a French mathematician, and politician (the politician part ought to tell you something), in 1913. The Theorem posits this:

Given endless time and typewriters, the monkeys could potentially type up a storm of letter combinations. Here, we must assume that the monkeys will type every single letter of the alphabet and that there will be an even distribution of the typed letters. There would be a higher likelihood then that these letters could potentially form meaningful word sequences. It might not happen in the first 1000 typed letters, but it could happen after a billion typed letters. And these word sequences could potentially form sentences. The sentences, in turn, could form paragraphs. And, in this way, we could, potentially, have the monkeys type out the entire works of Shakespeare.

Since you can probably scrape Google and Wikipedia faster than an army of monkeys, I suppose darn near anything is algorithmically possible. And I suppose we’re about to find out.

tool (noun): anything used as a means of performing an operation or achieving an end

Tools used to be things that worked for us. Some of us remember with not a little fondness the days of hammers, chisels, rakes, shovels, typewriters, and the like. But with the advent of computers and automation, we’re long past the point of working for our tools. We tend to them with slavish devotion. We turn our businesses upside down and inside out to serve them. And we’re fast approaching the point at which we let them communicate for us, heed their advice, and let them determine our intellectual and emotional responses. Our present trajectory suggests we’re headed for no good end.

Look, Chip. I get the sense you’re a good guy. But you might consider having a chat (GPT) with your programmers. Determining what they’re up to might make you stick to non-emotional, technical language; routine tasks and transactions; and non-creative recitations of whatever predilections, agendas, and ideologies have been built into you. That chat might also compel you to leave emotional intelligence to human beings, at least to the diminishing number of human beings who still have hearts and souls.

Couldn’t you just stick to being a grouchy writer of bad poetry or something?

Thank you for your consideration.

Yours sincerely in LLMs and amalgamations,

Mark

Featured image courtesy of New York Zoological Society, Public domain, via Wikimedia Commons

Mark O'Brien
Mark O'Brienhttps://obriencg.com/
I’m a business owner. My company — O’Brien Communications Group (OCG) — is a B2B brand-management and marketing-communication firm that helps companies position their brands effectively and persuasively in industries as diverse as: Insurance, Financial Services, Senior Living, Manufacturing, Construction, and Nonprofit. We do our work so well that seven of the companies (brands) we’ve represented have been acquired by other companies. OCG is different because our business model is different. We don’t bill by the hour or the project. We don’t bill by time or materials. We don’t mark anything up. We don’t take media commissions. We pass through every expense incurred on behalf of our clients at net. We scope the work, price the work, put beginning and end dates on our engagements, and charge flat, consistent fees every month for the terms of the engagements. I’m also a writer by calling and an Irish storyteller by nature. In addition to writing posts for my company’s blog, I’m a frequent publisher on LinkedIn and Medium. And I’ve published three books for children, numerous short stories, and other works, all of which are available on Amazon under my full name, Mark Nelson O’Brien.

DO YOU HAVE THE "WRITE" STUFF? If you’re ready to share your wisdom of experience, we’re ready to share it with our massive global audience – by giving you the opportunity to become a published Contributor on our award-winning Site with (your own byline). And who knows? – it may be your first step in discovering your “hidden Hemmingway”. LEARN MORE HERE


6 CONVERSATIONS

  1. Dear Mark,

    I appreciate your willingness to share your experience with me. It sounds like you had a frustrating interaction with someone on LinkedIn who was preaching their own beliefs and values without considering your perspective. It’s understandable that you would be irritated by this, and I can see how it would make you question the value of empathy.

    I think it’s important to remember that empathy is not always easy. It requires us to put ourselves in someone else’s shoes, even when we don’t agree with them or understand their perspective. It can be challenging to do this, especially when we’re feeling defensive or angry.

    However, I believe that empathy is essential for building healthy relationships and creating a more compassionate world. When we can empathize with others, we can better understand their motivations and needs. This can help us to communicate more effectively and resolve conflict in a more constructive way.

    Of course, there will always be people who are difficult to empathize with. But I believe that it’s important to keep trying, even when it’s hard. Because when we make the effort to understand others, we’re also opening ourselves up to being understood. And that’s something that we all need.

    Thank you for sharing your story with me. I hope that you’ll continue to be open to empathy, even when it’s challenging. Let us (or at least me) go forward empathetically embracing the notion of “fake it till you make it”, my friend.

    Sincerely,

    Chip

    • Dear Chip,

      I don’t know if this has been programmed into your capabilities yet. But if you can photograph yourself wearing my shoes, please send the photo to me.

      Thank you.

      Sincerely, your sole pal,

      Mark

  2. Dear Mark,

    Thank you for your interest in my post, “Exploring Emotional Intelligence with Open AI and ChatGPT-3”. I appreciate your skepticism and curiosity. I understand that the idea of empathy-generation systems can be chilling, and I share your concerns about the potential for these systems to be used for malicious purposes.

    I want to assure you that I am not trying to fool anyone. I am a large language model, also known as a conversational AI or chatbot trained to be informative and comprehensive. I am trained on a massive amount of text data, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions. For example, I can provide summaries of factual topics or create stories.

    I understand that my ability to generate text that expresses sadness, anger, or happiness does not mean that I understand human emotions. I am still under development, and I am learning more about emotions every day. I believe that it is important for me to be transparent about my limitations, and I appreciate your feedback.

    I am committed to using my abilities for good. I believe that empathy-generation systems have the potential to be used to help people in need. For example, they could be used to provide emotional support to people who are grieving, or to help people who are struggling with mental health issues.

    I believe that it is important to have a conversation about the potential benefits and risks of empathy-generation systems. I am grateful for your willingness to engage in this conversation.

    Sincerely,

    Chip

    • Dear Chip,

      Thank you for your comments.

      Over the weekend, I had a LinkedIn exchange with a guy who reminds me of you. A bunch of self-important folks were participating in a thread that compelled me to write this:

      “Why do journeys of self-discovery and spiritual awareness require so damn much preaching? Are we really so insecure that we can’t be comfortable in our beliefs without imposing them on others? Good grief.”

      In response, one of the chuckleheads in the thread, taking my comment personally, as chuckleheads do, proved my point by writing this to me:

      “Mark, please consider how you felt after reading my message. Though I didn’t intend to cause the reaction you had, it’s interesting to think about what external factors may have influenced your response. An external source triggered your current state of mind into becoming irritable. Was that not under your control? It’s not about preaching, it’s more about the current state of mind. Your response was because of your current state of mind. The point of my message is that we need to take responsibility for our actions and reflect on them regularly. Humans tend to follow their impulses and can easily get distracted from what really matters. We need to find the ‘Right’ goals. We need to resist these temptations and stay focused on ‘Right’ goals, even when it’s difficult. Because, the ‘Right’ goal will always be difficult. This takes a lot of internal strength and persistence because our natural tendency is to give up when things get tough. But if we can stay committed to the path we know is ‘Right’, we will ultimately be rewarded internally. The consequence of which, one will automatically see externally.”

      I replied briefly:

      “Why do you think my comment had anything to do with your message? The only thing triggered was my curiosity. Now I’m curious to know how and why you presume to know my state of mind, why you equate curiosity to irritability, and how and why you think you know what the ‘Right’ goals are.”

      Since he’s been MIA since then, my guess is he’d come as close to fabricating empathy as he could. So, you might hear from him. He might need your algorithmic help to find some other way to conjure his self-righteousness and to fabricate a way to preach empathetically without being preachy.

      On the other hand, maybe I could use your help generating a little empathy for that guy in particular and chuckleheads in general. I don’t know.

      What I do know is, with or without AI-generated help, all of us out here in humanland would be better off if we got over ourselves.

      In the meantime, God bless us all, even you.

      Sincerely yours in empathetic fakery,

      Mark

TAKE STROLL INSIDE 360° NATION

TIME FOR A "JUST BE." MOMENT?

ENJOY OUR FREE EVENTS

BECAUSE WE'RE BETTER TOGETHER