Purplehermann's Shortform

In general the human body is only capable of healing injuries that are the kind of thing that, if they were smaller, would still leave the victim alive, in the Stone Age.  If an injury is of a type that would be immediately fatal in the Stone Age, there’s no evolutionary pressure to make it survivable.  For example, we can regrow peripheral nerves, because losing a peripheral nerve means a numb patch and a weak limb, but you could live with this for a few months even if you’re a caveman.  On the other hand, we can’t regrow spinal cord, because a transected spinal cord  is fatal within a day or two even given the finest Stone Age nursing care (it didn’t become survivable until about 1946.). On the third hand, we can heal brain from strokes, even though brain is more complex than spinal cord, because a small stroke is perfectly survivable as long as you have someone to feed you until you get better.  We can survive huge surgical incisions, even though those would be fatal in the Stone Age, because small penetrating wounds were survivable, and the healing mechanisms can just do the same thing all along the incision.  This is why we sew wounds up: to convince the healing mechanisms that it’s only a small cut.

Unfortunately this argument suggests regrowing limbs is impossible.  An amputation is bad but survivable, and after it heals, you can still get around.  But many years of spending a lot of bodily energy on regrowing a limb that is pretty useless for most of that time doesn’t seem worthwhile.

Some particular problems I see:

In humans, there’s no mechanism for a growing limb to connect correctly to an adult injury site.  For example, there’s already a bunch of scar tissue there, which has to be cleared away progressively as the limb grows.  Evolution has not seen fit to provide us with this complex biochemistry, unlike the case of salamanders.

Children have a high level of circulating growth hormone, which tells the arm cells how fast to grow.  If you tried to provide this to an adult, their other bones would also grow, causing deformity (acromegaly).

It’s odd that we can’t grow new teeth when the old ones fall out.  More than once, I mean.  Drilling for cavities makes sense because the enamel (outer tooth layer) is essentially dead, and doesn’t regrow.  But we should be able to grow a whole new tooth from the root when we get a cavity.

The regrowing limb thing is a nonstarter due to the issue of time if I understand correctly. Salamanders that can regrow limbs take roughly the same amount of time to regrow them as the limb takes to grow in the first place. So it would be 1-2 decades before the limb was of adult size. Secondly it's not as simple as just smearing on some stem cells to an arm stump. Limbs form because of specific signalling molecules in specific gradients. I don't think these are present in an adult body once the limb is made. So you'd need a socket which produces those which you'd have to build in the lab, attach to blood supply to feed the limb, etc.

There seem to be clinical trials underway for regrowing teeth in Japan: https://www.popularmechanics.com/science/health/a60952102/tooth-regrowth-human-trials-japan/

This isn’t crazy— people have tried related techniques.  But it needs more details thought out. 

In the chess example, the AIs start out very stupid, being wired at random.  But in a game between two idiots, moving at random, eventually someone is going to win.  And then you reinforce the techniques used by the winner, and de-reinforce the ones used by the loser.  In any encounter, you learn, regardless of who wins.  But in an encounter between a PM and a programmer, if the programmer fails, who gets reinforced?  It might be because the programmer is dumb, and should be de-reinforced.  But it might be because the PM is dumb, and asked for something impossible or far beyond what can be done, in which case it should be de-reinforced.  But it might be because the PM came up with a task just barely beyond the programmer’s ability, which is good and should be reinforced.  We somehow need to keep the PM producing problems which are hard but possible.  Maybe the programmer could be tasked with coming up with either a solution or a proof of impossibility?  

AlphaGo had a mechanism which tracked how important each move was.  It was trained to predict the probability that white would win, on each position encountered in the game.    Moves where this probability swung wildly were given a larger weight in reinforcement.  This was important for concentrating training on decisive moves, allowing the extraction of information from each move instead of each game. It’s not clear if this is possible in the programming task.

What’s a PM?

Research companies work best when there's plenty of infrastructure that can supply stuff they need to do the research. Including, to mention one recent case, electricity [EA · GW]. It also helps to be in an area where there is stable government that can protect the research site from civil or military unrest, and too much (or too unpredictable) corruption. You also want it to be a place where your researchers are happy to live while they do their research, and where you can relatively easily recruit other skilled workers.

China does meet these requirements, but it is not exactly lacking in bureaucracy so I'm not sure why it made the list. If you're doing research involving human trials of some sort, you also want to be able to communicate well with the participants so extensive knowledge of the language and culture will be very useful.

All that said, plenty of organizations do carry out research all over the world, not just in rich countries with a lot of bureaucracy.

Speaking as a low-level employee in the medtech industry, I can report that a lot of companies are satisfied doing human research in Eastern Europe, where costs are low and regulations lax, but infrastructure is still available. I have heard that there is a bit of "rotation" among these countries over time, since costs and regulations tend to increase wherever human research becomes popular.

Well, no.  the easy part of a university undergrad education is pretty cheap (to provide) already.  It's bundled with a lot of things that make it expensive to buy traditionally.

Whether something is technically and economically possible is just a part of the puzzle. The remaining part is whether the people who make decisions have the incentives to do so.

According to Bryan Caplan, schools certify: intelligence, conscientiousness, and conformity. Online learning would certify intelligence, conscientiousness (even more than school attendance), but not conformity. Would the employers be okay with that?

Also, some prestigious universities select for having tons of money and/or the right social connections. The education is not the point. The point is that your parents had to be a part of the social "inner circle" to get you to the university, and you spent a few years socializing with other kids of the same kind, establishing the "inner circle" of the next generation. Making the credentials available to hoi polloi would defeat the entire purpose.