(cross-post from my blog) This post is the first in a series of notes on Reinforcement Learning. In the past few months, I have been learning about this topic, and I have found it completely fascinating. Aside from the computational beauty and usefulness of the algorithms, I find that it...
(This article is cross-posted from my blog) Imagine a world in which agents may interact, but may not coordinate in an enforceable way. Agents may communicate, but there is no mechanism to hold another agent accountable to commitments reached while communicating. In this world, all conflicts of interest between agents...
Actually I wonder if we could do an experiment in the following way:
It's true that there will be some amount of overlap, but this should put a ceiling on how well this approach could work.
I guess it’s about entropy. Some items have more entropy than others. They have more parts and more possible states, and most of those states are misconfigured.
A table or a chair has most of its parts glued together in a fixed, low-entropy position, and has few parts to begin with.
A printer has many parts, both at the hardware and software level, and they can be in many states. It has paper, which can be in a state of having run out or not, and if it has run out, the supply can be almost literally anywhere. It has many intricate mechanical parts which can wear out at different rates, it has an... (read more)
Where can one buy ostrich eggs?
This comic by Tim Urban is interesting, but I remember when I first read it, it seemed wrong.
In his framework, I think ASI can only be quantitatively more powerful than human intelligence, not qualitatively.
The reason is simple: humans are already Turing complete. Anything a machine can do, it can only be faster execution of something a human could already do.
I don’t think it has much bearing on the wider discussion of AI/AI-risk, I haven’t heard anybody else think that the distinction of quantitative/qualitative superiority had any bearing on AI risk.
I have similar problems, and I was hoping you had found a solution. One question I have: on a typical night, do you have good sleep quality, for example as measured by a fitness tracker?
Closest thing I have found to a solution of daily energy is creatine, 5g daily, and 10g if I did hard exercise that day. I cycle on it for about two weeks, until it starts to feel like too much of a good thing, then cycle off for a week, repeat.
Super interesting! I have some follow-up thoughts to this.
A classical example of the latter point is when novices learn to play chess. In a typical training session, they will be presented with a position, and be asked to propose a move. They will take a moment, then propose a move that loses a queen in a totally obvious way, and when challenged, they will take a moment... (read more)
I love this post, and I have been thinking a lot about it since it came out.
One counter argument I can think of is the following.
So one may argue that it’s rational to seek king-power on this basis
Despite this, I personally resonate very strongly with the image of the wizard, and I think the world would be a better place if we all sought to strengthen our wizarding powers.
Can you say more about what kind of changes you implemented?
A perhaps more interesting interaction is with wills that are managed by trusts. My understanding is that you can put conditions on how the money in a trust will be disbursed to your heirs, for example "as long as they maintain a minimum GPA in college". I have heard lawyers make outrageous jokes like adding a clause that says "as long as they don't marry that person".
It's quite reasonable to expect that some will add a clause to their trust that says "this only pays out if they have placed themselves on the lifetime no-gambling list".
(cross-post from my blog)
This post is the first in a series of notes on Reinforcement Learning.
In the past few months, I have been learning about this topic, and I have found it completely fascinating. Aside from the computational beauty and usefulness of the algorithms, I find that it provides an interesting framework to think about how I approach learning from experience in my own life.
Reinforcement Learning is a branch of AI that tries to develop agents that can learn interactively from real experience. The intelligent agent is assumed to have a set of sensors by which it can observe the world, a set of actuators by which it may act on the... (read 714 more words →)
(This article is cross-posted from my blog)
Imagine a world in which agents may interact, but may not coordinate in an enforceable way. Agents may communicate, but there is no mechanism to hold another agent accountable to commitments reached while communicating. In this world, all conflicts of interest between agents would resolve to a Nash Equilibrium.
A Nash Equilibrium, sometimes described as a "self-enforcing law", is an outcome from which no agent has an incentive to unilaterally deviate.
I will talk about the Prisoner's Dilemma, an illustration of a simple scenario that is famous because its Nash Equilibrium is /bad/. If the players could coordinate to escape the pull of the force that pulls them... (read 1445 more words →)
I’m confused—your examples for IVT reference “lumpy” functions. I’m not exactly sure what that means, but it seems like you mean functions with discrete, sharp steps. Such a function would be discontinuous, and IVT only applies to continuous functions.