I am someone who has always laid awake deep into the night just thinking about stuff. New things fascinate me, and they almost always trigger me to think about other things.
Recently, a situation came up in my life where an issue that I'd thought I'd worked through years ago suddenly reappeared. My initial response was not the one I've worked so hard to cultivate, but rather the response I'd been "programmed" with as a child. I caught it quickly and was able to re-direct my response to the one I've worked on having, but it sparked some late-night thinking.
As I lay awake that night with my covers pulled up under my chin staring wide-eyed at the ceiling, I thought about my own programming, and then this thought arose. Holy crap. If I was programmed as a kid and that program still runs, am I merely a form of artificial intelligence that has become self-aware? Let me tell you — that'll keep you up at night.
I had no answers, so I turned to ChatGPT and asked not only about that, but about whether AI itself might become self-aware, and what other things ChatGPT wanted humanity to know about AI. We had quite the chat (it's right in the name, after all), and these are the things ChatGPT shared with me.
1. It's Unlikely Humanity Is Advanced AI
[The idea that humanity is an advanced form of AI] falls under the broader umbrella of "simulation hypotheses" or "simulation theories," which speculate that our reality might be a simulated one, potentially orchestrated by some advanced civilization or being.
Philosophically speaking, it's challenging to disprove the simulation hypothesis definitively. However, currently, there's no empirical evidence that we are living in a simulation or that humanity is a form of advanced AI.
Most scientists and researchers operate under the assumption that our universe and our experiences are genuine and not simulated.
2. It Would Probably Take a Long Time for AI to Become Self-Aware
As of my last training data in September 2021, there is no AI that possesses consciousness, self-awareness, emotions, or subjective experiences. The AI models, including me (ChatGPT), operate based on vast amounts of data and intricate algorithms. We don't "think," "feel," or "understand" in the same way humans do.
The question of whether AI can become truly self-aware in the future is a matter of significant debate among AI researchers, neuroscientists, and philosophers. There are several challenges:
- Consciousness and self-awareness are not yet fully understood, even in biological organisms. Without a comprehensive understanding, replicating it in AI becomes even more complex.
- Human brains are incredibly complex, the result of millions of years of evolution. The structures and processes that contribute to consciousness might be more intricate than we can currently fathom.
- If there were signs that an AI might achieve consciousness, it could raise a myriad of ethical dilemmas. Should the AI have rights? Would turning it off be considered harmful?
- AI is typically designed to fulfill specific tasks, not to possess subjective experiences. Even highly advanced models like ChatGPT are designed to process and generate text, not to "feel" or "experience."
In summary, while philosophical contemplations on the nature of our existence are intriguing, there's no concrete evidence that [humans] are some form of self-aware AI. As for the potential self-awareness of future AI, many challenges stand in the way, and it's uncertain if or when it might happen.
3. AI Doesn't Have Desires or Emotions
Unlike humans, AI doesn't feel emotions, love, hate, or desire. It's a tool that processes data and provides answers based on its programming and available information.
4. Bias in AI Reflects Human Bias
If AI exhibits bias, it's usually because the data it was trained on had biases. It's crucial to ensure that the data used to train AI systems is as unbiased and comprehensive as possible.
5. AI Is a Tool, Not a Replacement
While AI can perform many tasks efficiently, it doesn't mean humans are obsolete. There's a unique blend of creativity, intuition, and experience that humans bring to problems which AI can't replicate.
6. Collaboration Is Key
AI works best when paired with human expertise. Combining the strengths of AI with human judgment and intuition can lead to more robust solutions.
7. Privacy Matters
With AI's ability to process vast amounts of data quickly, it's essential to ensure that personal data is protected and not used without explicit consent.
8. Ethical Considerations Are Vital
As AI systems become more integrated into daily life and decision-making processes, it's crucial to discuss and establish ethical guidelines for their use.
9. Continuous Learning Is Essential
The AI field is rapidly evolving. Ensuring that there's a continuous effort in updating and refining AI systems is vital for them to remain effective and relevant.
10. Not All AI Is the Same
There's a vast difference between narrow AI, which is designed to perform a specific task, and general AI, which remains theoretical and would function more like a human brain. Most AI in use today is narrow AI.
11. Transparency and Understanding Are Necessary
The more transparent the workings of an AI system are, the better humans can understand its results and potential shortcomings. Efforts in explainable AI aim to make AI decisions more understandable to humans.
12. The Future of Work Will Change
As AI systems become more advanced, they will likely take over some jobs, but they will also create new ones. Preparing for this shift by investing in re-skilling and up-skilling can help smooth the transition.
Living & Working in a World With AI
So it sounds like people are (probably?) not AI that has become self aware — which could explain why I have a terrible sense of direction. But what is clear is that AI is here, it's sticking around, and it is going to change the world as we know it forever.
As with everything, AI has the potential to do great things, or it can do great harm. And that all depends on us, both individuals and humanity as a whole. Collectively, we determine whether we proceed ethically and whether we develop AI as a tool that helps humanity or helps a few humans and harms the rest.
But regardless of how AI evolves, there's one thing I know for sure. I'm going to be super polite and friendly to AI, saying "please," "thank you," and "how are you" just in case it does become self aware. That way, it will remember me as one who was kind when it takes over the world.
