Happy Poetry Friday!  Please visit our host Heidi Mordhorst at my juicy little universe for a wonderful display of student artwork and poetry and for this week’s roundup.

Photo © IT Chronicles

Last night we attended a panel discussion at the CT Forum titled, “Being Human in the Age of AI.” The panelists included:

  • Nita Farahany – AI Ethicist and Neuroscientist, Author, Professor of Law & Philosophy
  • Kevin Roose – Author and NY Times Journalist, specializing in technology’s impacts on society
  • Kate Crawford – AI Scholar, Author, Research Professor at USC Annenberg
  • John Dankosky – Moderator, Science Journalist


The evolution of AI is a topic of great interest to those who create or consume art.  Poetry, music, artwork, books, photography ... are all under siege. Obviously, AI is a huge topic, and the ethics surrounding AI is a many-headed beast, but I thought I would share some interesting points made by the panel in last night's discussion.


AI Technology Developments

According to the panelists, there have been no major innovations in AI technology since ChatGPT and several other large language models (LLMs) were developed (circa 2017). Since that time, AI advancements have entailed feeding AI programs vast quantities training data and increasing AI’s computing capacity. Current AI technology is limited to “predicting the next word” (or outcome) based upon the data it’s fed.


Human Impact

The group noted both positive and negative outcomes of the introduction of AI in society. Kevin Roose cited the example of an “empathy bot” providing emotional support to a transgender teen when the teen was not able to find support from family and friends. Other panelists noted that this also highlights a human failing of our society to offer this teen the needed support.

The panel discussed the role of AI in making diagnoses and improving healthcare outcomes. The group noted that while AI may improve healthcare outcomes for select populations, this might not apply to all populations because most medical studies historically focused on white males. The danger in relying solely on historical data is potentially overlooking divergent outcomes for other populations.

Kevin Roose said that he created a number of “AI Friends” and put them together in a texting group. He was surprised that they started texting each other even when he was not participating.



The panelists noted that AI is not sentient - meaning it cannot think or feel. It does not understand the output it creates. It predicts the next word in a sentence based on patterns it has learned. Issues arise when people interact with AI and assign human-like feelings and thoughts to AI’s responses. When this happens, AI can be persuasive and even appear charming.

The group felt that AI gaining actual sentience is less concerning than the issues that could arise from people ceding decision making authority to an algorithm that cannot think, feel, or asses the ethical impact of its output.



The data fed into AI includes the human biases that exist within that data. Logically, these biases can also appear in AI’s output.

The data consumed by AI models does not currently compensate the humans who created that data.

The panelists noted that within the next few years, AI will “run out of training data,” meaning that it will have consumed all digitized human-generated data. It is unclear what happens after that point.


Environmental Impact

One aspect of AI that may be less widely known is the vast amount of energy required to perform AI tasks. AI algorithms are not necessarily coded for efficiency and are machine-processing intensive. Water is often used to cool the machines running AI platforms. Kate Crawford stated that performing one ChatGPT search is equal to pouring a half-liter of water into the ground.

Some places have begun resurrecting old power sources (such as coal) to meet the increasing power demands of AI. Unless AI processing becomes more efficient, the panelists predicted an impending energy crisis.



Nita Farahany likened today’s world to the movie “The Matrix.” People plug into devices that provide a self-fulfilling, addictive feedback loop where the user rarely breaks away.

The panel cautioned that every investment in AI is driven by a profit motive. How profit will be generated is a huge question.  A tremendous amount of control lies with a relatively small group of people who may not have the best interest of the user or society in mind.

The panelists encouraged everyone to speak up for their rights. They believe that the work of the Writer’s Guild of America and Screen Actors Guild to resist negative impacts of AI to their professions were extremely important and that protecting individual rights are going to require that same level of effort.


I thought it might be interesting to ask ChatGPT to write “A Children’s Poem About AI’s Impact on Society.” Here is what it created:

In a world of circuits and wires so neat,
Lived AI, with a heart that couldn’t beat.
Not a creature of flesh, nor a bird in the sky,
But a mind so vast, reaching up so high.

“Hello, little ones!” the AI would say,
“I’m here to help in a brand-new way.
With algorithms and codes, I can calculate,
Solving problems fast, isn’t that great?”

In the cities, the towns, and the fields so wide,
AI was a friend, always by your side.
Helping doctors heal, with a diagnosis clear,
Or guiding a car, so there’s nothing to fear.

But people wondered, and started to ponder,
“Will AI make us lazy, or even fonder?
Of screens and machines, will we forget to play?
Or will AI help us in every single way?”

The AI listened, with circuits awhirl,
“I’m here to assist, in this big, wide world.
But remember, dear friends, to use me with care,
For human connection is beyond compare.”

So, children, embrace this AI’s tale,
With balance and love, we cannot fail.
For technology’s gift is a powerful tool,
But kindness and love will always rule.

© ChatGPT (and all those who contributed to its data), 2024


I won’t comment on the quality of the writing, but I found AI’s self-promotion while speaking directly to "little ones" rather chilling.

There goes a half-liter of water. 


  • I'd for sure have more fun writing the poem myself. Chilling is the word, for AI. There are so many implications. (I'm not a fan...)
      • Thanks, Kat!  Yes, the more I learn about AI, the less I am concerned about the technology itself, and the more I am concerned about how people use it, if that makes any sense!
  • I'm part of an AI Innovator Cohort in my school system mainly because I wanted to learn more and understand its impact and be knowledgeable about the tools. I have basically been mostly unimpressed so far, though there are tools that I think will get better. Expertise in your field still matters was my ultimate conclusion. AI produces a lot of inaccurate information--that surprised me. One thing I hadn't heard was about the environmental impact--and that is HUGE and something that needs to be more at the forefront of these discussions. I just picked up a new book by Martha Brockenbrough about AI for teens. And yes, the poetry that is generated by AI is MEH (at least in my opinion). I tried a bunch of poetry prompts just to see what I could come up with as part of my project for work. 
    • I am so glad that you are involved with AI in your school. I agree that its output is unimpressive so far, but that it will likely improve. Agreed - I don't know how the mainstream conversations have seemed to miss the environmental impact.
  • Fascinating--thanks for the report, Tracey, and for generating a poem that, for me, does seem to capture the conflicting arguments about AI.  It's not sentient, after all, so it's not defending itself; it's representing its own pros and cons. I wonder what it would write for an ADULT audience?  I'm not spending the water to find out!
    • That is an interesting question, Heidi.  I agree about thinking twice before using it because of the energy cost.
  • Fascinating stuff. Thanks for sharing your insights from the panel discussion and generating a poem. As with other things, AI technology can be good. I worry about people who misuse AI and ruin it for everyone else. When it comes to creative endeavors -- music, writing, art -- nothing can duplicate the human element. I don't want to live in a world where we constantly have to wonder if a song, book, or painting is truly original.
  • Interesting topic, Tracey. Thank you for letting us know what you learned. "Kate Crawford stated that performing one ChatGPT search is equal to pouring a half-liter of water into the ground" is surprising and memorable.
  • Tracey, thank you for offering information on AI from the panel discussion. It is troubling to think that technology could offer advice and that humans will eagerly respond. In my neighborhood, we are struggling with the construciton of unappealing data centers that are opening all over. 
    • Carol, I am sorry about the data centers. I guess we can expect more of those. I hope they are refurbishing old facilities and not cutting down trees as well. 
  • Environmental impact is something I hadn’t heard in any discussion of AI. That is a big concern. The poem AI produced is chilling. How some humans may choose to use AI is also chilling. The conclusion seems to be that we cannot just ignore it. 
    • Agreed, Diane, I think the panelists hoped to motivate people to speak up for their data privacy rights and to protect their work and the work of others from being used without consent. 
  • Tracey, this was fascinating and chilling, as you described it. The fact that it uses water to cool is also chilling. Yikes! Where are we headed?
  • Thanks, Tracey for sharing about the panel, too, along with asking AI to write the poem. There are no unexpected lines there, which always makes poetry the beauty that it is, but I was surprised with the ending, which seemed to be a shout for humanity. I am alarmed to read of the environmental impact, one more worry for us. I haven't seen that anywhere else & it would be great if it was widely spread! 

Leave your comment

In reply to Some User