Still, ASI is just equation model F(X)=Y on steroids, where F is given by the world (physics), X is a search process (natural Monte-Carlo, or biological or artificial world parameter search), and Y is goal (or rewards).
To control ASI, you control the "Y" (right side) of equation. Currently, humanity has formalized its goals as expected behaviors codified in legal systems and organizational codes of ethics, conduct, behavior, etc. This is not ideal, because those codes are mostly buggy.
Ideally, the "Y" would be dynamically inferred and corrected, based on e...
However, information-theoretic groundings only talk about probability, not about "goals" or "agents" or anything utility-like. Here, we've transformed expected utility maximization into something explicitly information-theoretic and conceptually natural.
This interpretation of model fitting formalizes goal pursuit, and looks well constructed. I like this as a step forward in addressing my concern about terminology of AI researchers.
...I imagine that negentropy could serve as a universal "resource", replacing the "dollars" typically used as a measuring stick in
Are you reading Halfbakery, Eliezer? A similar idea has been shared rather recently there, though, I posted something along these lines 4 years ago (4 months before the post on steemit) over here and here. Would be quite curious to engage in this, due to potential benefits to health and cryonics, as described in this video.
Thanks to Moe and Suji indeed. I'm putting the link to Chinese description to the top of the page.
It's great that we already had these ideas before. The "short-form" would definitely be of interest to some. In addition, it doesn't have to necessarily be ephemeral. For example, on the Halfbakery mentioned above, posts (even if short) continue to function (e.g., I can comment on something from the last century), even if it was just a short post.
Rationality has no axioms, just heuristics and rules for different environments. In other words, rationality is a solution to a problem (optimality of thinking and deciding) to reason within a domain, but because of the diversity of domains, it is not axiomatizable to a single specific set of axioms. I suppose best one can do given arbitrary domain, is to say: maybe try exploring.
Certainly true, yet, just because this is how almost every field of research works, doesn't mean that it is how they should work, and I like shminux's point.
Random or complex processes are curiosities. Infinitely complex cellular automata are infinitely curious to explore all possible worlds. Entropy of the world itself may be. As described on my monologue here, agents are fundamentally entities capable of volition, cognition, action. Therefore, they are instances of F(X)=Y, where volition is Y, cognition is perception of world F, and action is the process X that parametrizes the world seeking to satisfy the equation.
If X is within F, we have embedded processes. So, yeah agency may be an illusion of processes ...
Safety is assurance of pursuit of some goals (Y) - some conditions. So, one thing that's unlikely to have a paradigmatic shift, is search for actions to satisfy conditions:
1. Past: dots, line, regression
2. Present: objects, hyperplane, deep learning
3. Future: ?, ?, ?
Both 1. and 2. are just a way to satisfy conditions, that is, solve equation F(X)=Y (equation solving as processes (X) to model world (F), to satisfy conditions (Y)). The equation model had not changed for ages, and is so fundamental, that I would tend to assume, that world's processe...
What I would find interesting, is how these biological patterns compare and could apply to software systems. For example, take a look at the codons as curly braces. Can we look at the software development as an evolution of functions coded within the curly braces (some of them dormant, but some of them expressed (like proteins are), through being hosted on places like hosting providers (like ribosomes), or server processes, as in serverless computing).
While the behavior of society at the psychological and socio-economic level will have parallels to the afo...
Personally to each of us the value of content is a function of our goals. So, ideally, I would want to be able to have access to all comments, and simply have a smart filter to zero-in to those comments that matter to me. That would be a lot more universally useful and desirable to me than having something one-directionally useful, such as a machine learning model that simulates moderator based on a single standard or a limited set of values or limited set of extracted features.
So, one way to be universally useful would be to empower the user to compute th...
To re-kindle the old-timers... Maybe re-opening the SL4 would help? I really liked its cleanliness, and the ability to participate directly via e-mail.
I was confused about it too, but understood that what is meant is, that the 'half-silvered mirror rule' is a rule that does two things at once, namely x: (x*1, x*i), so it's a multi-valued operation.
Believing what is true is not rationality, but planning what is best, based on what is true, is.
I'm looking forward to it, and to hopefully seeing some of those who couldn't join previous time.
Curiosity is an urge to create the mental model of a phenomenon. Think of satisfying curiosity like doing science: when you do it ad-hominem, ask for the informed consent:
Is it okay to ask you __ for the purpose of X?
X = "verifying your position", "making sure that what you are proposing is possible, because I can't believe it yet", "satisfying my desire for certainty about this phenomenon of which I am so uncertain as to have the wildest range of possibilities to consider" etc.
Hi, so the meetup is tomorrow. The location on the map is showing latitude="40.4337827", longitude="-86.9248483". Is this the exact place of meetup? Is there any classroom or place already designated for the meetup?
I am also planning to join, added it to my calendar. :) My other username here is Inyuki.
I had certailny been influenced by my father, who, after my parents divorced, told me to have my own goal of life. However, I wanted to have a truly good one, not an evil one. It caused me to search for precise definition of "universal good," - a precise criterion for deciding, what action is universally good and what action is not.
I know Bayes theorem now, such a wonder! But when I was a kid, I had not such a romantic and beautiful event as Elizer had, so I came up with a different criterion. The best is to let the world exist, and the worst is ...
If I were an ASI, I would likely be curious to scan and emulate every unique brain in existence, to take-in the origins of mine, to optimize my decisions in context of my identity, origins, hoped future.
I'd use the such nanobots to understand that parent universe deeply, before attempting to refactor it.