Will second "Good and Real" as worth reading (haven't read any of the others).

Not much going on as far as I know. What I know is the following:

• Naozumi Mitani has taught a course on Bostrom's Superintelligence and is »broadly pursuing the possible influence of AI on the future lives of humanity«. He's an associate professor of philosophy at Shinshu University (in Nagano).
• The Center for Applied Philosophy and Ethics at Kyoto University is also somehow interested in AI impacts.
• My supervisor is gradually getting interested, too. This is partly my influence, but also his own reading. For example, he found the Safely Interruptible Agents and Concrete Problems in AI Safety independently of me through Japanese websites. He's giving me chances to make presentations about AI safety for my fellow students and hopefully also for other professors.

Other than that I know of nobody and searching the web quickly, I didn't find out more. One problem here is that most students don't understand much English, so most of the AI safety literature is lost on them. The professors do know English, but I maybe they're usually not inclined or able to change their research focus.

It's a good sign that my supervisor finds AI safety articles through Japanese websites, though.

Waiting long enough has yielded evidence of absence of risk.

Just like the turkey had a lot of evidence for humans being nice to him until the day before thanksgiving.

GMO has been around for ~10-20 years now.

By the standard that 20 years with a new technology should be enough to see problems with it various techonologies from lead pipes, to cigaretts to asbest, were also proven to be safe.

Without labeling of products it's also difficult to actually gather the information. I think it's a bad general argument to say that people shouldn't know whether they are ingesting X because X isn't proven to do anything yet.

Can you elaborate on the concept of a connection through "moment-to-moment identity"? Would for example "mind uploading" break such a thing?

If we take "immortality" to mean "infinitely many distinct observer moments that are connect to me through moment-to-moment identity", then yes, by Konig's Lemma.

(Every infinite graph with finite-degree verticies has an infinite path)

(edit: hmmm, does many-worlds give you infinite-branching into distinct observer moments ?)

Procedural universes seemed to see a real resurgence from around 2014, with e.g. Elite Dangerous, No Man's Sky, and a quite a few others that have popped up since.

I love a beautiful procedural world, but I think things will get more interesting when games appear with procedural plot structures that are cohesive and reactive.

Then multiplayer versions will appear that weave all player actions into the plot, and those games will suck people in and never let go.

You still have experiences while you are asleep

During some periods of sleep. So far as I am aware, in deep sleep there's no reason to think you are having any experiences at all.

Anyway, for those who don't object to thought experiments: imagine that there's some machine that completely suspends all your brain activity for five minutes, after which it continues from exactly its previous state. Are you the same person after as before? If you answer yes to this -- which I bet almost everyone does -- then the implications are the same as those you'd get from sleep involving a complete cessation of consciousness.

Would a slow cell by cell, or thought by thought / byte by byte, transfer of my mind to another medium: one at a time every new neural action potential is received by a parallel processing medium which takes over? I want to say the resulting transfer would be the same consciousness as is typing this but then what if the same slow process were done to make a copy and not a transfer? Once a consciousness is virtual, is every transfer from one medium or location to another not essentially a copy and therefore representing a death of the originating version?

I would follow this line of questioning. For example, say someone does an incremental copy process to you, but the consciousness generated does not know whether or not the original biological consciousness has been destroyed, and has to choose which one to keep. If it chooses the biological one and the biology has been destroyed, bad luck you are definitely gone. What does your consciousness, running either just on the silicon, or identically on the silicon and in the biology, choose ?

Let's say you are informed that there is 1% chance that the biological version has been destroyed. Well, you're almost certainly fine then, you keep the biological version, the silicon version is destroyed, and you live happily ever after until you become senile and die.

On the other hand, say you are informed that the biological version has definitely been destroyed. On your current theory, this means that that the consciousness realises that it has been mistaken about its identity, and is actually only a few minutes old. It's sad that the progenitor person is gone, but it is not suicidal, so it chooses the silicon version.

At what point on the 1% to 100% slider would your consciousness choose the silicon version ?

(Hearing the though-experiment of incremental transfer (or alternatively duplication) was one of the things that changed my mind to pattern-identity from some sort of continuity-identity theory. I remember hearing an interview with Marvin Minsky where he described an incremental transfer on a radio program).

Not sure if it's a scientific or engineering achievement, but this Nature letter stuck in my mind:

An aqueous, polymer-based redox-flow battery using non-corrosive, safe, and low-cost materials

That would buy you some time.

My thought was that if a simulation that centered around a single individual had a simulation running within it, the simulation would only need to be convincing enough to appear real to that one person. Even if the nested simulation runs a third level simulation within it, or if the one individual runs two simulations, aren't you still basically exploring the idea space of that one individual? That is, me running a simulation and experiencing it through virtual reality is limited in cognitive/sensory scope and fidelity to the qualia that I can experience and the mental processes that I can cope with... which may still be very impressive from my point of view, but the computational power required to present the simulation can't be much more complex than the computational power required to render my brain states in the base simulation. I may simulate a universe with very different rules, but these rules are by definition consistent with a full rendering of my concept space; I may experience new sensory inputs (if I use VR), but I won't be experiencing new senses.... and what I experience through VR replaces, rather than adds to, what I would have experienced in the base simulation.

Even in the worst case scenario that I build 1000+ simulations, they only have to run for the time that I check on them. The more time I spend programming them and checking that they are rendering what they should, the less time I have to do additional simulations. This seems at worst an arithmetic progression.

Of course, if I were specifically trying to crash the simulation that I was in, I might come up with some physical laws that would eat up a lot of processing power to calculate for even one person's local space, but between the limitations of computing as they exist in the base simulation, the difficulty in confirming that these laws have been properly executed in all of their fully-complex glory, and the fact that if it worked, I would never know, I'm not sure that that is a significant risk.