# Gurkenglas

Karma: 623

NewTop

Links to the papers would be useful.

It seems to me like the conditional oracle’s definition could be made more elegant by taking only m and n as a parameter, both of which take an action as a parameter. The oracle would then implement .

I would like to read more of that meta-reasoning log. Is it public?

Presumably, it is a random number generator hooked up to motor controls. There is no explicit calculation of utilities that tells it to twitch.

According to GAZP vs. GLUT with consciousness replaced by goal-directed behavior, we may want to say that goal-directed behavior is involved in the creation or even just specification of the giant lookup table TicTacToe agent.

Maximizing the sum of the difference of state value just maximizes state value again, which the point of narrow reinforcement learning was to get away from.

Narrow reinforcement learning: As A

Wouldn’t it try to bring about states in which some action is particularly reasonable? Like the villain from that story who brings about a public threat in order to be seen defeating it.

Could we budget our trust in a predictor by keeping track of how hard we’ve tried to maximize predicted approval? Let Arthur expect any action to have a chance to get its approval overestimated, and he will try proposing fewer alternatives. Just like when frequentists decrease p-value thresholds as they ask more questions of the same data. To avert brainwashing the real Hugh, assume that even asking him is just a predictor of the “true” approval function.

The situation seems to me comparable to one where we upload Hugh and then let him do what he wants, such as optimizing himself by replacing parts of himself by machine learning predictors with correlating results. The hope here then sounds like that this is fine so long as we perform differential testing to limit accidental drift.

QM-based realities may just be amenable to containing fusion or planets or amino acids.

We then loop over each action a and take the action with the highest expected answer.

Wasn’t the whole point that we want to avoid such goal-direction?

We could say that Hugh must first approve of the strategy in your first paragraph, but that lands us in a bootstrapping problem.

How does this differ from just running Hugh?

#3:

on shortens all distances but is strictly monotonic.

#6: (the “show that if” condition follows from the property, the question is likely misstated)

The iteration is so long that it must visit an element twice. We can’t have a cycle in the order so the repetition must be immediate.

#1

Let f be such a surjection. Construct a member of P(S) outside f’s image by differing from each f(x) in whether it contains x.

#2

A nonempty set has functions without a fixed point iff it has at least two elements. It suffices to show that there is no surjection from S to S → 2, which is analogous to #1.

#3

T has only one element. Use that one.

#7 Haskell

source = “main = putStrLn (\“source = \” ++ show source ++ \“\\n\” ++ source)”

main = putStrLn (“source = ” ++ show source ++ “\n” ++ source)Is #8 supposed to read “Write a program that

**takes**a function f taking a string as input**as input**, and produces its output by applying f to its source code. For example, if f reverses the given string, then the program should outputs its source code backwards.“?If so, here.

source = “onme = putStrLn $ f $ \“source = \” ++ show source ++ \“\\n\” ++ source”

onme f = putStrLn $ f $ “source = ” ++ show source ++ “\n” ++ source

Turning each node but the last blue from left to right conserves the parity of the bichromatic edge count at each step until it is still odd at the end.

If #4 is true, it is provable:

If #4 is true, changing the color of a single node (except to forbidden colors on edges) cannot change the parity of the trichromatic triangle count, and this would be checkable through a finite case analysis of graphs of size <=7. Given that lemma, we can recolor one corner to red, the remainder of one large edge blue and the remaining nodes green, producing the odd count 1.

#8:

We are looking for a surface [0,1]²->[0,1] whose intersection with the plane x=y does not contain a function of t. It suffices to show that the intersection looks like the letter s, with exactly the endpoints reaching t=0 or t=1. It suffices to show that the intersection can be any continous function of x including the points t=x=y=0 and t=x=y=1. Within each plane of constant x, define the surface as 0 for small t, 1 for large t, and rapidly rising through the plane x=y wherever we want the intersection.

Correct. A candidate for a common causal factor of blaming the new media is observing that the young people are wrong.

If we taboo the evidence of subjectively observing the people raised by the new media, what remains is the filter bubble effect. It seems in hindsight like a natural rationalization to reach for, because it’s one of the few known downsides of the internet. Eliezer, you wrote the book on noticing when you rationalize. Is this a likely story?

Are some parts of the internet more affected by the new effects of the internet than others? Is there a way to test them for their cognitive function as opposed to thinking in ways the previous generation wouldn’t approve of?

This pattern matches for me to how every generation thinks the new form of media will harm the next generation, all the way back to Socrates thinking writing will destroy people’s memory.

Does becoming the stereotypically biased geezer seem plausible to you who wrote that he might hit a brick wall at 40, or is this outside-view thinking asking the wrong questions?

What did he need that assumption for? If the setting is that two AIs try to convince a human audience, the assumption doesn’t seem to enter into it. The important question is presumably what friendliness properties we can deduce about any AI that wins the debate against every other AI.