TsviBT(Tsvi Benson-Tilsen)

• TsviBT 21 Apr 2024 20:05 UTC

  3 points

  0

  in reply to: yanni’s comment on: yanni’s Shortform

  This practice doesn’t mean excusing bad behavior. You can still hold others accountable while taking responsibility for your own reactions.

  Well, what if there’s a good piece of code (if you’ll allow the crudity) in your head, and someone else’s bad behavior is geared at hacking/​exploiting that piece of code? The harm done is partly due to that piece of code and its role in part of your reaction to their bad behavior. But the implication is that they should stop with their bad behavior, not that you should get rid of the good code. I believe you’ll respond “Ah, but you see, there’s more than two options. You can change yourself in ways other than just deleting the code. You could recognize how the code is actually partly good and partly bad, and refactor it; and you could add other code to respond skillfully to their bad behavior; and you can add other code to help them correct their behavior.”. Which I totally agree with, but at this point, what’s being communicated by “taking self-blame” other than at best “reprogram yourself in Good/​skillful ways” or more realistically “acquiesce to abuse”?

Koan: di­v­in­ing alien datas­truc­tures from RAM activations

• TsviBT 2 Apr 2024 19:38 UTC

  LW: 6 AF: 5

  2

  AF

  on: The Shut­down Prob­lem: In­com­plete Prefer­ences as a Solution

  IDK if this is a crux for me thinking this is very relevant to stuff on my perspective, but:

  The training procedure you propose doesn’t seem to actually incentivize indifference. First, a toy model where I agree it does incentivize that:

  On the first time step, the agent gets a choice: choose a number 1--N. If the agent says k, then the agent has nothing at all to do for the first k steps, after which some game G starts. (Each play of G is i.i.d., not related to k.)

  So this agent is indeed incentivized to pick k uniformly at random from 1--N. Now consider:

  The agent is in a rich world. There are many complex multi-step plans to incentivize agent to learn problem-solving. Each episode, at time N, the agent gets to choose: end now, or play 10 more steps.

  Does this incentivize random choice at time N? No. It incentivizes the agent to choose randomly End or Continue at the very beginning of the episode, and then carefully plan and execute behavior that acheives the most reward assuming a run of length N or N+10 respectively.

  Wait, but isn’t this success? Didn’t we make the agent have no trajectory length preference?

  No. Suppose:

  Same as before, but now there’s a little guy standing by the End/​Continue button. Sometimes he likes to press button randomly.

  Do we kill the guy? Yes we certainly do, he will mess up our careful plans.

• TsviBT 24 Mar 2024 14:16 UTC

  3 points

  0

  in reply to: bullet645_throwaway’s comment on: What in­for­ma­tion do you share with whom?

  I think it’s a norm if you’re bidding for specific attention, yeah. Like, you should either do more work to figure out a smaller set of people who you want to bid for attention from, or else at least say that you haven’t done that work.

• TsviBT 24 Mar 2024 14:15 UTC

  3 points

  1

  in reply to: bullet645_throwaway’s comment on: What in­for­ma­tion do you share with whom?

  The examples in this comment are about “oops I had an idea that sounds good but is accidentally bad”. That’s a reasonable thing to worry about but doesn’t seem like the thing you were actually asking about. You wrote:

  I don’t expect to be particularly good at coordinating with my perfect clones for example. I’m sure if you put me in a room with my perfect clone and a source of massive power (such as a controllable ASI), we’d beat each other half to death fighting for it.

  This seems much more central, and indicates a major problem.

• TsviBT 24 Mar 2024 6:56 UTC

  3 points

  0

  in reply to: bullet645_throwaway’s comment on: What in­for­ma­tion do you share with whom?

  Is this referring to my insights in particular or something similar somebody else said?

  It’s meant to gesture at a category of thinking, a given instance of which may or may not be worthwhile or interesting, but which leads people to be very overly worried about the consequences of spreading the ideas involved, compared to how bad the consequences actually are. For example, sometimes [people who take hypothetical possibilities very seriously] newly think of something, such as the potential of BCIs or the potential of thinking in such-and-such unconventional way or whatever. Then they implicitly reason like this: There’s a bunch of potential here; previously I hadn’t thought of this idea; previously I hadn’t pursued efforts related to this idea; now I’ve thought of this idea; the fact that I just now thought of the idea and hadn’t previously explains away the fact that I haven’t previously pursued related efforts; so probably my straightforward inside view of why there’s potential here is correct or at least a good rough draft guess; which means there are huge implications here; and the reason others aren’t pursuing related efforts is probably that they didn’t think of the idea; and since the idea is powerful, I shouldn’t share it.

  Usually some but not all of these inferences are correct. Often the neglectedness is mainly because others don’t believe in hypothetical possibilities, not because no one has thought of it. Rarely does the final inference go through.

  I’ve already had conversations with multiple billionaires.

  I would think the problem here would be failing at transfering the relevant info, not transfering too much info!

  But if you manage to get their attention you could get them to copy your preferred choices instead.

  The only morally acceptable thing to copy in this way is an orientation against making decision this way.

• TsviBT 24 Mar 2024 4:32 UTC

  8 points

  2

  on: What in­for­ma­tion do you share with whom?

  For the most part, if you have a reason to share some information, you should share it. For the most part, trying to make a bunch of information boundaries will cripple your ability to do anything useful, and doesn’t avert much bad stuff. Your amazing strategic insights about how we’re all swimming in a sea of hyperstitious memetic warfare and therefore we can control the future by blah blah are usually false, and not actually that big if true because in general things are more in equilibrium than they seem and more driven by forces you’re not controlling than they seem. The more open I am about things I thought I should be cagey about, the more I find no one cares. Unless you’ve got a lot of attention for some reason, roughly no one cares about what you think enough to do much of anything in response to what you think.

  There are obvious exceptions, like not sharing other people’s personal info in public or not sharing your garage nuke technology.

  Distinguish [trust to not harm you, e.g. by misusing info you’ve shared] from [trust to meet your efforts toward a shared goal]. The latter is generally more important than the former, because lifeforce is a pretty limited resource, so you have to know where to invest yours.

• TsviBT 24 Mar 2024 4:20 UTC

  2 points

  0

  in reply to: bullet645_throwaway’s comment on: What in­for­ma­tion do you share with whom?

  I think it’s pretty defecty to email a lot of people without saying in the email that you’ve done so.

• TsviBT 15 Mar 2024 1:49 UTC

  7 points

  1

  in reply to: Ricki Heicklen’s comment on: Toward a Broader Con­cep­tion of Ad­verse Selection

  Bad restaurants are more likely to have open tables than good restaurants.

  That seems dependent on it being difficult to scale the specific skill that went into putting together the experience at the good restaurant. Things that are more scalable, like small consumer products, can be selected to be especially good trades (the bad ones don’t get popular and inexpensive).

• TsviBT 15 Mar 2024 0:32 UTC

  2 points

  0

  on: Toward a Broader Con­cep­tion of Ad­verse Selection

  Bruh. Banana Laffy Taffy is the best. Happy to trade away non-banana to receive banana, 1:1.

[Question] What could a policy ban­ning AGI look like?

• TsviBT 20 Jan 2024 3:59 UTC

  3 points

  −3

  in reply to: James Camacho’s comment on: What Soft­ware Should Ex­ist?

  The point of the essay is to describe the context that would make one want a hyperphone, so that

  1. one can be motivated by the possibility of a hyperphone, and

  2. one could get a hold of the criteria that would direct developing a good hyperphone.

  The phrase “the ability to branch in conversations” doesn’t do either of those.

• TsviBT 20 Jan 2024 0:07 UTC

  5 points

  0

  on: What Soft­ware Should Ex­ist?

  Quoting another comment I made:

  Make a hyperphone. A majority of my alignment research conversations would be enhanced by having a hyperphone, to a degree somewhere between a lot and extremely; and this is heavily weighted on the most hopeworthy conversations. (Also sometimes when I explain what a hyperphone is well enough for the other person to get it, and then we have a complex conversation, they agree that it would be good. But very small N, like 3 to 5.)

  https://​​tsvibt.blogspot.com/​​2023/​​01/​​hyperphone.html

• TsviBT 18 Jan 2024 23:00 UTC

  3 points

  0

  in reply to: Chipmonk’s comment on: Views on when AGI comes and on strat­egy to re­duce ex­is­ten­tial risk

  Yes.

• TsviBT 2 Jan 2024 15:37 UTC

  2 points

  0

  in reply to: the gears to ascension’s comment on: A hermeneu­tic net for agency

  It’s a makeshift stop-gradient. I less feel like I’m writing to LessWrong if I’m not publishing it immediately, and although LW is sadly the best place on the internet that I’m aware of, it’s very much not in aggregate a gradient I want. Sometimes I write posts intended for LW and publish them immediately.

A hermeneu­tic net for agency

• TsviBT 18 Dec 2023 23:42 UTC

  9 points

  3

  on: The ‘Ne­glected Ap­proaches’ Ap­proach: AE Stu­dio’s Align­ment Agenda

  Make a hyperphone. A majority of my alignment research conversations would be enhanced by having a hyperphone, to a degree somewhere between a lot and extremely; and this is heavily weighted on the most hopeworthy conversations. (Also sometimes when I explain what a hyperphone is well enough for the other person to get it, and then we have a complex conversation, they agree that it would be good. But very small N, like 3 to 5.)

  https://​​tsvibt.blogspot.com/​​2023/​​01/​​hyperphone.html

• TsviBT 18 Dec 2023 20:55 UTC

  LW: 2 AF: 1

  0

  AF

  in reply to: Nora_Ammann’s comment on: Non-di­rected con­cep­tual found­ing

  I’m not sure I understand your question at all, sorry. I’ll say my interpretation and then answer that. You might be asking:

  Is the point of the essay summed up by saying: ” “Thing=Nexus” is not mechanistic/​physicalist, but it’s still useful; in general, explanations can be non-mechanistic etc., but still be useful, perhaps by giving a functional definition of something.”?

  My answer is no, that doesn’t sum up the essay. The essay makes these claims:

  1. There many different directions in conceptspace that could be considered “more foundational”, each with their own usefulness and partial coherence.

  2. None of these directions gives a total ordering that satisfies all the main needs of a “foundational direction”.

  3. Some propositions/​concepts not only fail to go in [your favorite foundational direction], but are furthermore circular; they call on themselves.

  4. At least for all the “foundational directions” I listed, circular ideas can’t be going in that direction, because they are circular.

  5. Nevertheless, a circular idea can be pretty useful.

  I did fail to list “functional” in my list of “foundational directions”, so thanks for bringing it up. What I say about foundational directions would also apply to “functional”.

• TsviBT 18 Dec 2023 20:39 UTC

  2 points

  0

  in reply to: romeostevensit’s comment on: What is wis­dom?

  Hm, ok, thanks. I don’t I fully understand+believe your claims. For one thing, I would guess that many people do think and act, under the title “Buddhism”, as if they believe that desire is the cause of suffering.

  If I instead said “Clinging/​Striving is the cause of [painful wheel-spinning in pursuit of something missing]”, is that any closer? (This doesn’t really fit what I’m seeing in the Wiki pages.) I would also say that decompiling clinging/​striving in order to avoid [painful wheel-spinning in pursuit of something missing] is tantamount to nihilism. (But maybe to learn what you’re offering I’d have to do more than just glance at the Wiki pages.)

• TsviBT 18 Dec 2023 20:30 UTC

  LW: 10 AF: 4

  0

  AF

  on: The Short­est Path Between Scylla and Charybdis

  As you can see, the failures lie on a spectrum, and they’re model-dependent to boot.

  And we can go further and say that the failures lie in a high-dimensional space, and that the apparent tradeoff is more a matter of finding the directions in which to pull the rope sideways. Propagating constraints between concepts and propositions is a way to go that seems hopeworthy to me. One wants to notice commonalities in how each of one’s plans are doomed, and then address the common blockers /​ missing ideas. In other words, recurse to the “abstract” as much as is called for, even if you get really abstract; but treat [abstracting more than what you can directly see/​feel as being demanded by your thinking] as a risky investment with opportunity cost.