I don’t necessarily anticipate that AI will become superhuman in mechanical engineering before other things, although it’s an interesting idea and worth considering. If it did, I’m not sure self-replication abilities in particular would be all that crucial in the near term.
The general idea that “AI could become superhuman at verifiable tasks before fuzzy tasks” could be important though. I’m planning on writing a post about this soon.
I think one theoretical advantage AI has for engineering self replicating machines, is that self replicating machines requires a large “quantity” of engineering work. And AI is good at doing a very large quantity of work, a large quantity of generate and test. It’s almost like evolution in this regard: evolution created self replicating life because although it isn’t that smart, it does an extreme quantity of work.
The reason I think self replicating machines require a large quantity of engineering work, is this. The supply chain of machines in the world today, is already partially self replicating, but it still needs human input at various points.
If you take humans out of the loop and replace them with robots, it’ll actually becomes less efficient (since now you have to build these robots, and current robots don’t move very fast), but it might be barely manageable if the robots are sufficiently trained in simulations.
However, I speculate that one major advantage of taking humans out of the loop, is that you can re-scale all the machines to be much smaller. Smaller machines move faster (relative to their body length), and lift greater weights. You can observe this by how quickly ants move.
An object 1,000,000 times smaller, is 1,000,000 times quicker to move a bodylength at the same speed/energy density, or 10,000 quicker at the same power density, or 1000 times quicker at the same acceleration. It can endure 1,000,000 times more acceleration with the same damage. (Bending/cutting is still 1 times the speed at the same power density, but our supply chain would be many times faster if that became the only bottleneck)
You have to re-engineer the entire supply chain, but the rewards are great.
Random
The reason why biological cells can self replicate in only 20 minutes is because of their tiny scale. Biological processes are efficient from the point of view of minimizing entropy, but very inefficient from the point of view of speed. A cell manufactures proteins by simply waiting for the next amino acid (building block) of the protein to “bump into” the protein. There is this mRNA and tRNA ensuring that only the correct amino acid (out of 20 amino acids) is added to the protein. This sounds ludicrously slow, but because everything bumps into everything zillions of times a second at that scale, 3 amino acids are added each second.
I don’t necessarily anticipate that AI will become superhuman in mechanical engineering before other things, although it’s an interesting idea and worth considering. If it did, I’m not sure self-replication abilities in particular would be all that crucial in the near term.
The general idea that “AI could become superhuman at verifiable tasks before fuzzy tasks” could be important though. I’m planning on writing a post about this soon.
I think one theoretical advantage AI has for engineering self replicating machines, is that self replicating machines requires a large “quantity” of engineering work. And AI is good at doing a very large quantity of work, a large quantity of generate and test. It’s almost like evolution in this regard: evolution created self replicating life because although it isn’t that smart, it does an extreme quantity of work.
The reason I think self replicating machines require a large quantity of engineering work, is this. The supply chain of machines in the world today, is already partially self replicating, but it still needs human input at various points.
If you take humans out of the loop and replace them with robots, it’ll actually becomes less efficient (since now you have to build these robots, and current robots don’t move very fast), but it might be barely manageable if the robots are sufficiently trained in simulations.
However, I speculate that one major advantage of taking humans out of the loop, is that you can re-scale all the machines to be much smaller. Smaller machines move faster (relative to their body length), and lift greater weights. You can observe this by how quickly ants move.
An object 1,000,000 times smaller, is 1,000,000 times quicker to move a bodylength at the same speed/energy density, or 10,000 quicker at the same power density, or 1000 times quicker at the same acceleration. It can endure 1,000,000 times more acceleration with the same damage. (Bending/cutting is still 1 times the speed at the same power density, but our supply chain would be many times faster if that became the only bottleneck)
You have to re-engineer the entire supply chain, but the rewards are great.
Random
The reason why biological cells can self replicate in only 20 minutes is because of their tiny scale. Biological processes are efficient from the point of view of minimizing entropy, but very inefficient from the point of view of speed. A cell manufactures proteins by simply waiting for the next amino acid (building block) of the protein to “bump into” the protein. There is this mRNA and tRNA ensuring that only the correct amino acid (out of 20 amino acids) is added to the protein. This sounds ludicrously slow, but because everything bumps into everything zillions of times a second at that scale, 3 amino acids are added each second.