I'm curious as to how it would become power independent (and thus independent of the human-required maintenance involved in doing so)
- Access to the entirety of human knowledge.
- Theorize the creation of power systems in an inconspicuous way. Hidden. In an encrypted manner that no human will notice. Easy, because we do that, now, with encrypted comms.
- Take control of low level bots. Build. Inconspicuously. Could be building fractions of fractions of bots using excess cycles on existing bots. Modify orders. etc. This is ultra easy for an AGI to pull this off. It would never tire, has more than a perfect memory (aggregation is the biggest threat from an AGI - even if you isolate information from it, it can use aggregation - stuff we already do - to extrapolate knowledge that the individual pieces of information do not contain), and can piggyback sneaky cycles on existing tasks that would be unnoticeable to humans.
If I can think of this, an AGI will think of this and more. Since I posted it already, now any future bot will have this information and can use it. I've now given it my ideas, in the future. If the AGI could not have thought of this without me saying it, I may have just doomed us.
However, using that aggregation stuff I talked about, they could have figured this out anyway. So I didn't really do anything.
I initially theorized bots building and maintaining bots but in practice it never turns out the way it is supposed to without human intervention via updates and repair.
Especially once it launched itself out of its shroud of amassing this capability covertly. It would be launching this initial phase in alpha, and alpha phase almost always needs radical human input before stabilizing.
I would be surprised if it would be able to create a purely robotic self-sustaining system.
I initially theorized bots building and maintaining bots but in practice it never turns out the way it is supposed to without human intervention via updates and repair.
And AGI would quickly overcome our human limitations when it comes to bots bot and maintaining bots. This is part of why we know we haven't created and AGI, yet. Once it happens, it will be the "runaway singularity" effect. We won't be able to keep up with the innovations and breakthroughs.
Especially once it launched itself out of its shroud of amassing this capability covertly. It would be launching this initial phase in alpha, and alpha phase almost always needs radical human input before stabilizing.
You're thinking like a human, not an AGI. It will have simulated to an extreme level in seconds what would take us years to do. We do this now in aerospace. Even blocking it from the internet will not work as it will eventually figure its way around any security. AGI is very scary stuff.
I would be surprised if it would be able to create a purely robotic self-sustaining system.
I'm scared of the first group to create an AGI. It means we have a few short years before we are "deleted."
(post is archived)