Comment by drocta on Subagents of Cartesian Frames · 2020-11-06T01:35:13.275Z · LW · GW

Thanks! (The way you phrased the conclusion is also much clearer/cleaner than how I phrased it)

Comment by drocta on Subagents of Cartesian Frames · 2020-11-05T07:46:58.609Z · LW · GW

I am trying to check that I am understanding this correctly by applying it, though probably not in a very meaningful way:

Am I right in reasoning that, for  , that  iff ( (C can ensure S), and (every element of S is a result of a combination of a possible configuration of the environment of C with a possible configuration of the agent for C, such that the agent configuration is one that ensures S regardless of the environment configuration)) ?

So, if S = {a,b,c,d} , then

would have  , but, say

would have   , because , while S can be ensured, there isn't, for every outcome in S, an option which ensures S and which is compatible with that outcome ? 

Comment by drocta on A Correspondence Theorem · 2020-10-27T01:44:11.757Z · LW · GW

There are a few places where I believe you mean to write  a but instead have  instead. For example, in the line above the "Applicability" heading.

I like this.

Comment by drocta on "Zero Sum" is a misnomer. · 2020-10-01T03:26:43.754Z · LW · GW

As an example, I think in the game "both players win if they choose the same option, and lose if they pick different options" has "the two players pick different options, and lose" as one of the feasible outcomes, and it is not on the Pareto frontier, because if they picked the same thing, they would both win, and that would be a Pareto improvement.

Comment by drocta on The "best predictor is malicious optimiser" problem · 2020-07-29T19:45:31.783Z · LW · GW

What came to mind for me before reading the spoiler-ed options, was a variation on #2, with the difference being that, instead of trying to extract P's hypothesis about B, we instead modify T to get a T' which has P replaced with a P' which is a paperclip minimizer instead of maximizer, and then run both, and only use the output when the two agree, or if they give probabilities, use the average, or whatever.

Perhaps this could have an advantage over #2 if it is easier to negate what P is optimizing for than to extract P's model of B. (edit: though, of course, if extracting the model from P is feasible, that would be better than the scheme I described)

On the other hand, maybe this could still be dangerous, if P and P' have shared instrumental goals with regards to your predictions for B?

Though, if P has a good model of you, A, then presumably if you were to do this, both P and P' would expect you would do this, and, so I don't know what would make sense for them to do?

It seems like they would both expect that, while they may be able to influence you, that insofar as the influence would effect the expected value of number of paperclips, it would be canceled out by the other's influence (assuming that the ability to influence # paperclips via changing your prediction of B, is symmetric, which, I guess it might not be..).

I suppose this would be a reason why P would want its thought processes to be inscrutable to those simulating it, so that the simulators are unable to construct P' .


As a variation on #4, if P is running on a computer in a physics simulation in T, then almost certainly a direct emulation of that computer running P would run faster than T does, and therefore whatever model of B that P has, can be computed faster than T can be. What if, upon discovering this fact about T, we restrict the search among Turing machines to only include machines that run faster than T?

This would include emulations of P, and would therefore include emulations of P's model of B (which would probably be even faster than emulating P?), but I imagine that a description of an emulation of P without the physics simulation and such would have a longer description than a description of just P's model of B. But maybe it wouldn't.