I’ve been watching Lex Fridman’s podcasts in 2023; they are a good source of learning. Lex interviewed Ray Kurzweil on 17 September 2022; these are my lessons learned.
Singularity
Ray wrote his book The Singularity Is Near: When Humans Transcend Biology in 2005; it’s one of my favorite books. I bet I’ve read it five times. The first questions Lex asks Ray are: What’s the technological singularity? And when will it happen?
Ray answers twice in the interview: “The singularity is where computers really change our view of what’s important and change who we are. … by the time you get to 2045, we’ll be able to multiply our intelligence many millions-fold. And it’s very hard to imagine what that would be like.”
For background, here’s the definition of the technological singularity from Wikipedia: “The technological singularity—or simply the singularity is a hypothetical future point in time at which technological growth becomes uncontrollable and irreversible, resulting in unforeseeable changes to human civilization. According to the most popular version of the singularity hypothesis, I.J. Good’s intelligence explosion model, an upgradable intelligent agent will eventually enter a “runaway reaction” of self-improvement cycles, each new and more intelligent generation appearing more and more rapidly, causing an “explosion” in intelligence and resulting in a powerful superintelligence that qualitatively far surpasses all human intelligence.”
I asked ChatGPT 3.5 similar questions:
ChatGPT 3.5 – The singularity is a hypothetical future point in time at which technological growth will become so rapid that humanity will be irreversibly transformed. Some people believe that the singularity will bring about a utopian future, while others are more skeptical and believe that it could potentially have negative consequences. There is no consensus on when or if the singularity will occur. Some believe that it may happen within the next few decades, while others think that it is much further off or may never happen at all.
JB – Will the singularity happen in 2045?
ChatGPT 3.5 – There is no way to predict with certainty when or if the singularity will occur. Some people, including the mathematician and computer scientist Vernor Vinge, have speculated that the singularity could happen as soon as 2045, but this is just an educated guess and there is no evidence to support this claim. The concept of the singularity is based on the idea that technological progress will eventually become so rapid that it will lead to significant changes in society and the human condition. However, there are many factors that could influence the pace of technological progress and it is difficult to accurately predict how these factors will play out in the future.
So, why does Ray think a technological singularity will occur in 2045? Because he has extrapolated the performance of computing hardware and software from historical trends to predict the increasing exponential growth of technology.
It leads to a question, how good are Ray’s predictions? He also predicted a computer would pass a Turing test by 2029; this prediction is coming to pass with the advent of artificial intelligence tools like Chat GPT4. Ray is likely correct that artificial intelligence will exceed human intelligence and that it’s difficult to predict beyond this event. Ray’s book The Singularity is Near details this case; I will reread it and write my thoughts. I look forward to reading Ray’s forthcoming book: The Singularity is Nearer.
Brain-computer interfaces
Ray’s view on brain-computer interfaces: “….. there are some prototypes where you can connect your brain. They actually don’t have the amount of bandwidth that we need. They can work, but they work fairly slowly.
So if it actually would connect to your neocortex. And the neocortex, which I describe in How to Create a Mind, the neocortex, it has different levels, and as you go up the levels, it’s kind of like a pyramid. The top level is fairly small and that’s the level where you want to connect these brain extenders. So I believe that will happen in the 2030s. … So just the way this {smartphone} is greatly amplified by being connected to the cloud, we can connect our own brain to the cloud and just do what we can do by using this machine. “
Brain-computer connections to the neocortex will happen, but there is a stumbling block: neuroscience needs to understand the interface definition between the brain and a machine.There is much to learn about the brain. Developments in hardware are only one of the primary drivers of progress. Communications between the human brain and a machine require fundamental neuroscience breakthroughs that answer the question: what is the brain’s primary language? How does the brain communicate with itself? [1]
As a cross-check, I asked ChatGPT 3.5 JB – What are the technical challenges to connect a human neocortex to a computer?
ChatGPT 3.5 – There are many technical challenges that would need to be overcome in order to connect the human neocortex to a computer in a way that would allow for the transfer of cognitive functions or experiences. Some of the main challenges include:
- Developing a way to interface with the brain: In order to connect the neocortex to a computer, scientists would need to develop a way to interface with the brain and record or stimulate the activity of individual neurons. This is a very complex task, as the brain is composed of billions of neurons and trillions of connections, and it is not yet fully understood how these neurons and connections work together to produce thoughts, feelings, and behaviors.
- Mapping the brain’s activity: In order to connect the neocortex to a computer, scientists would need to create a map of the brain’s activity and understand how different patterns of activity correspond to specific thoughts, feelings, and behaviors. This is a very difficult task, as the brain is a highly dynamic and complex system, and it is not yet fully understood how different patterns of activity are related to specific mental states.
- Developing a way to transfer information between the brain and a computer: Scientists would need to develop a way to transfer information between the brain and a computer in a way that is fast, accurate, and biocompatible. This would require the development of new technologies and materials, as well as a better understanding of how the brain processes and stores information.
- Overcoming ethical concerns: There are many ethical concerns that would need to be addressed in order to connect the human neocortex to a computer. For example, there are questions about the potential risks and benefits of such a connection, as well as concerns about the impact on an individual’s sense of self and personal identity.
The second challange identified by ChatGPT 3.5 Mapping the brain’s activity was similar to my concern. I think Chat GPT did a better job than me in summarizing this concern. I think mapping the brain’s activity is much more challenging than developing the interface and the information transfer methods. I don’t mean to trivialize these concerns, the interface and transfer of information are difficult bioengineering challenges.
A major benefit of asking ChatGPT about the technical challenges to connect a human neocortex to a computer – it brought to my attention the ethical concerns. Honestly, I had not thought about this important issue.
Meaning of Life
Ray and Lex broadly discussed consciousness, uploading minds, nanotechnology, the digital afterlife, and other topics. There was a bond between these two humans; they smiled and laughed at points in the interview.
Despite this primarily technical conversation, when Lex asked Ray the meaning of life, Ray said: “Love. Because if there were no love and we didn’t care about anybody, there’d be no point existing.”
Final Quote from Lex
Lex closes the interview with a quote from Issac Asimov: “It is change, continuous change, inevitable change that is the dominant factor in society today. No sensible decision could be made any longer without taking into account not only the world as it is, but the world as it will be. This in turn means that our statesmen, our businessmen, our everyman, must take on a science fictional way of thinking.” (from the book “Asimov on Science Fiction“)
I pondered these words from one of my favorite authors; we must look ahead. Ray Kurzweil is a guiding light as we navigate an unknown future.
Notes
[1] These questions came from John von Neumann as discussed in Bhattacharya, A. (2022). The Man from the Future: The Visionary Ideas of John von Neumann. Here’s the quote from Chapter 1 of the book: “What then, he asked, is the brain’s primary language? How does the brain communicate with itself? This is a question that he would continue to wrestle with, even on his deathbed.” I need to write a review of this excellent book.
[2] I made a Transcript of Lex Fridman Interview with Ray Kurzweil It’s a useful adjunct to the video.
[3] Here’s a post with some more details on my questions for ChatGPT 3.5 Singularity and other questions ChatGPT 3.5 session I need to repeat these questions with ChatGPT 4 and later versions.
brewbooks 
One thought on “Lessons learned from Lex and Ray Kurzweil (Lex Fridman Podcast #321)”