Ourselves, Our Posterity
In this second look at artificial intelligence, we explore its potential, define its scope, dive into superintelligence, and share fun, productive ways to use ChatGPT.
In our first look at artificial intelligence (AI), we explored its good, bad, and sometimes scary potential. Here’s the link.
This issue spans fun ways to use ChatGPT to a frightening aspect of AI. We’re going deeper, unpacking what AI is, how it works, and where it’s already part of our lives.
As we continue to explore, “Ourselves, Our Posterity” remains committed to encouraging thoughtful engagement, critical thinking, and a legacy of responsibility. Join us as we consider the impact of machines that can learn and adapt—asking not just what AI can do but also reminding us of what we should do for ourselves and our posterity.
What Is Artificial Intelligence?
Perhaps the best way to understand what AI is is to start with what it’s not. Let’s compare it to a calculator. While calculators are excellent tools for computation, they lack the adaptive qualities that define AI.
A calculator can't adapt to new situations. AI can.
It can't learn from new information. AI does.
It can't improve its performance over time. AI does.
AI systems are designed to learn and evolve, making them far more versatile and powerful. The technology is designed to mimic human-like thinking and decision-making processes. Here’s a quick breakdown of what AI does:
AI processes large amounts of data quickly and efficiently.
It recognizes trends and patterns within the data.
It makes decisions faster than humans can.
It continuously improves its performance through learning techniques.
AI You’re Already Using
You might not realize it, but AI is already part of your everyday life. Here are a few examples:
Spell checkers use AI to detect and correct spelling errors in real time.
Grammarly provides suggestions for grammar, style, and clarity powered by AI.
Siri and other virtual assistants respond to voice commands and perform tasks for you.
Search engines like Google rely on AI to understand queries and deliver relevant results.
Artificial intelligence isn’t just a concept of the future—it’s already shaping the tools we rely on daily, making life more efficient and convenient.
What is ChatGPT?
Chat3.5 was launched on November 30, 2022. There were earlier versions, but this is the one that started all the chatter. GPT stands for
Generative - It can generate new content based on patterns and information it has been taught.
Pretrained - It’s been trained to recognize patterns, including language patterns.
Transformer - The “transformer” aspect was a little more technical than I could understand, so I asked ChatGPT to explain it to me as if I were a child.
Its response was 148 words long. I told you in last week’s issue the app is chatty. Here’s my edited version of 50 words.
ChatGPT transforms how we teach computers about language. Imagine a magic robot that reads all the words in a story at once. It can focus on different parts of the story at the same time, even if the words are jumbled. And it can also make up a new story.
Fun Ways to Use ChatGPT
Let it plan your next vacation. I grew bored while standing in the endless line at the airport Starbucks. Rather than be strategic and download the app to place my order, I decided to have ChatGPT plan a future trip to Croatia for me. I told it how many days I wanted to visit and my interests. Then, in a matter of seconds, it gave me an itinerary. I don’t know when I’ll make it to Croatia, but the app is a good travel agent.
Here are other ways to have fun with ChatGPT or other chatboxes.
Don’t know what to make for dinner? Tell ChatGPT the ingredients you have on hand, and it will suggest a recipe. Sadly, it doesn’t cook or clean up.
My knowledge of poetry and poets is lacking, so now and then, I ask it to give me a poem. It is limited to older poems in the public domain to ensure it doesn’t violate copyright but I’m OK with Emily Dickinson, Robert Frost, and Langston Hughes.
I’m a trivia lover, so my family knows never to call me during Jeopardy. If you want to sharpen your knowledge on topics like mythology, geography, or major historical events, ask it to create a trivia game.
Looking to update your workout playlist? Ask ChatGPT to suggest ten songs with 120 or more beats per minute. Several of the songs it listed for me were already on my playlist, so I just had it give me ten more. You can use ChatGPT to offer suggestions for other types of playlists, such as road trips, relaxation, or motivational.
The Limits of AI “Creativity”
In the last issue, I shared part of a conversation I had with ChatGPT.
At one point, Chat described itself as “creative.” My follow-up question was.
ME: If you don't have thoughts or feelings, how can you be creative?
CHAT: You raise a valid point. When I mention creativity, it refers to my ability to generate novel and unique outputs based on the patterns and information I've learned from the training data.
Artificial, unlike human intelligence, cannot interact the way humans do. Humans draw from
Personal experience
Personal insights
Original thoughts
Emotions
Connection with the world and others.
AI, on the other hand, draws from
Patterns
Statistical analysis
GIGO–Garbage in, garbage out. If incorrect, outdated, or biased data is inputted, then the output–the information we’re provided–is unreliable and potentially harmful.
Not a Prophet, But…
I’m not a techie, nor am I a prophet. But as you read this poem written by my 14-year-old self, perhaps it will bring your thoughts to what ChatGPT cited as one of the possible dangers of AI: superintelligence.
Epistle To Be Left On Earth
I did not mean to do all this,
To take away the reason for living,
The reason for work, play, love, and success.
And the reason for leisure.
Leisure
The reward for work.
I had forgotten the meaning.
My invention
The ultimate in inventions (or so I thought).
Man would live the life of comfort.
No need to study or work.
No need to think for himself.
I knew that.
But I was looking for fame, for fortune!
I got it……..but for what?
Man lived a life of play, of leisure, of comfort.
It did not take long, though
For his mind to rot, for his trust to disappear.
Trust
The lack of it is what killed man.
The accusing, the greed, the hating.
One by one, man left this earth.
I tried to stop them, to save them, but their greed was worse than mine.
I tried to destroy the machine.
Like I said, though, it is the ultimate in inventions.
Man is now extinct, or nearly.
I am left.
I’ll die soon, if not of loneliness, then of shame.
Will you ever, God, forgive me?
Forgive us?
What a fool I have been.What fools we have all been.
Superintelligence: Is it a possibility?
Superintelligence is defined by Nick Bostrom of the Oxford Future of Humanity Institute as “an intellect that is much smarter than the best human brains in practically every field, including scientific creativity, general wisdom, and social skills.” Similarly, Miriam-Webster defines it as “an entity that surpasses humans in overall intelligence or in some particular measure of intelligence.”
You may recall from last week that I interviewed ChatGPT the way I would a human. Its responses ranged from humorous to thought-provoking and were very verbose. Thus, the editor in me shortened some of the responses.
Here’s what was shared about superintelligence.
ME: Do you think AI is dangerous to humanity?
CHAT: The question of whether AI is dangerous to humanity is a complex and debated topic. AI, like any powerful technology, has the potential for both positive and negative impacts. Here are some perspectives to consider:
Potential for superintelligence: The concept of superintelligent AI, where AI systems surpass human intelligence, raises theoretical concerns about control and alignment. Ensuring that highly intelligent AI systems align with human values and goals is a topic of ongoing research.
Researchers and Rogue Machines
Based on the response, I wondered how we prevent the machines from taking over. Just pull the plug is a response to dealing with the possibility of AI going rogue. But Stuart Russell warns in his book Human Compatible: Artificial Intelligence and the Problem of Control, “Switching the machines off won’t work for the simple reason that a superintelligent entity will already have thought of that possibility and taken steps to prevent it.”
On the other hand, computer scientist Manuel Alfonseca and a team of researchers published findings regarding controlling AI in the Journal of Artificial Intelligence. Alfonseca concedes, “It may be impossible to control superintelligent AI.” However, the research indicates It will be at “least two centuries” before the technology reaches a level of superintelligence in the form of being able to. Plus, researchers do not know if it is even possible to develop a machine as intelligent in every field as humans.
How to Counteract the Machines
Will the machines take over the world? I think not. Well, I hope not. But scientists, lawmakers, and business leaders must still consider the potential risks of artificial intelligence on humanity. The issue is mind-boggling. I do know this, though. Regardless of technology’s abilities, it's critical for each of us to continually sharpen our ability to think rationally and logically while working on consistently treating others well.
My 14-year-old self was a reflective soul. Decades later, I’m both optimistic and realistic.
AI challenges us to think deeply about what it means to be human. As we embrace its possibilities, let’s also commit to strengthening our values, sharpening our minds, and enriching our connections.
What role will you play in ensuring a legacy of thoughtful innovation? Leave a comment.
Sources:
Bostrom, Nick. How Long Before Superintelligence? Oxford Future of Humanity Institute
Choi, Charles Q. Institute of Electrical and Electronics Engineers; January 2021. Accessed May 29, 2023; Superintelligent AI May Be Impossible to Control; That's the Good News - IEEE Spectrum
Miriam-Webster.com. Miriam-Webster defines; accessed May 29, 2023
Russell, Stuart. Institute of Electrical and Electronics Engineers; Oct. 2019; accessed May 29, 2023; https://spectrum.ieee.org/many-experts-say-we-shouldnt-worry-about-superintelligent-ai-theyre-wrong