Jeffrey’s Reviews > The Singularity Is Nearer: When We Merge with AI > Status Update

Kurzwell estimates that nano computation outperforms mammalian neuron firing by 1 billion fold

Prob overly optimistic about the timeline for the singularity, clinical trials take a long time. But if the connection were non invasive , just a cap or earbud and this secured a connection to AI, that would be amazing. Then enhancing our bodies thru wearable prostheses that would enhance our strength , endurance and other capabilities ( jump? Fly?), what a world

Now he’s gotten a little far out – nano bots that repair human tissues by the 2030s? Nothing in medicine that revolutionary could move that quickly. It is just impossible.

Ancient Greek (recorded by Plutarch)
The Ship of Theseus
is an ancient philosophical thought experiment that questions whether an object remains the same when all of its components are gradually replaced. It explores the nature of identity, demanding to know if the newly constructed object is the original or entirely new. As each plank rots it is replaced. At what point is it a new ship?

Fascinating
External consciousness versus internal consciousness. Very difficult to prove or even understand the nature of internal consciousness it’s existence, evidence that it is functioning , so external consciousness serves as a proxy. The presence of an internal consciousness implies we must recognize that entity morally.

The other form of AI is neural networks, using a brute force approach with vast amounts of data to sit through and see patterns identify patterns that would’ve been in perceptible to humans in one form called unsupervised learning. Again weaknesses include air, accumulation, lack of knowledge of what the goal is or even what a correct answer is, takes vast machine, power, and vast data sets.

That’s called the complexity ceiling.

Ch 1
Rules based AI comma adds points for mistakes with each rule. Therefore, the more complex the algorithm the higher, the error rate.

Ch 1
The touring test, can be failed by the AI being too smart, and therefore recognizable as machine instead of human,? Is this wrong - the machine being too smart? The machine having achieved this goal and surpass it is probably a better explanation.