“I hereby precommit to make my decisions regarding whether or not to blackmail an individual independent of the predicted individual-specific result of doing so.”
“I hereby precommit to make my decisions regarding whether or not to blackmail an individual independent of the predicted individual-specific result of doing so.”
I’m afraid your username nailed it. This algorithm is defective. It just doesn’t work for achieving the desired goal.
Two can play that game.
The problem is that this isn’t the same game. A precommitment not be successfully blackmailed is qualitatively different from a precommitment to attempt to blackmail people for whom blackmail doesn’t work. “Precomittment” (or behaving as if you made all the appropriate precomittments in accordance with TDT/UDT) isn’t as simple as proving one is the most stubborn and dominant and thereby claiming the utility.
Evaluating extortion tactics while distributing gains from a trade is somewhat complicated. But it gets simple and unambiguous is when the extortive tactics rely on the extorter going below their own Best Alternative to Negotiated Agreement. Those attempts should just be ignored (except in some complicated group situations in which the other extorted parties are irrational in certain known ways).
“I am willing to accept 0 gain for both of us unless I earn 90% of the shared profit” is different to “I am willing to actively cause 90 damage to each of us unless you give me 60″ which is different again to “I ignore all threats which involve the threatener actively harming themselves”.
What I think is being ignored is that the question isn’t ‘what is the result of these combinations of commitments after running through all the math?’. We can talk about precommitment all day, but the fact of the matter is that humans can’t actually precommit. Our cognitive architectures don’t have that function. Sure, we can do our very best to act as though we can, but under sufficient pressure there are very few of us whose resolve will not break. It’s easy to convince yourself of having made an inviolable precommitment when you’re not actually facing e.g. torture.
We can talk about precommitment all day, but the fact of the matter is that humans can’t actually precommit.
If you define the bar high enough, you can conclude that humans can’t do anything.
In the real world outside my head, I observe that people have varying capacities to keep promises to themselves. That their capacity is finite does not mean that it is zero.
We can talk about precommitment all day, but the fact of the matter is that humans can’t actually precommit.
Pre-commitment isn’t even necessary. Note that the original explanation didn’t include any mention of it. Later replies only used the term for the sake of crossing an inferential gap (ie. allowing you to keep up). However, if you are going to make a big issue of the viability of precommitment itself you need to first understand that the comment you are replying to isn’t one.
That wasn’t a Causal Decision Theorist attempting to persuade someone that it has altered itself internally or via an external structure such that it is “precommited” to doing something irrational. It is a Timeless Decision Theorist saying what happens to be rational regardless of any previous ‘commitments’.
ur cognitive architectures don’t have that function. Sure, we can do our very best to act as though we can, but under sufficient pressure there are very few of us whose resolve will not break.
I’m aware of the vulnerability of human brains, so is Eliezer. In fact the vulnerability of human gatekeepers to influence even by humans, much less super-intelligences is something Eliezer made huge deal about demonstrating. However this particular threat isn’t a vulnerability of Eliezer or myself or any of the others who made similar observations. If you have any doubt that we would destroy the AI you have a poor model of reality.
It’s easy to convince yourself of having made an inviolable precommitment when you’re not actually facing e.g. torture.
For practical purposes I assume that I can be modified by torture such that I’ll do or say just about anything. I do not expect the tortured me to behave the way the current me would decide and so my current decisions take that into account (or would, if it came to it). However this scenario doesn’t involve me being tortured. It involves something about an AI simulating torture of some folks. That decision is easy and doesn’t cripple my decision making capability.
As I pointed out in another thread, “irrational behavior” can have the effect of precommitting. For instance, people “irrationally” drive at a cost of more than $X to save $X on an item. Precommitting to buying the cheapest product even if it costs you money for transportation means that stores are forced to compete with far distant stores, thus lowering their prices more than they would otherwise. But you (and consumers in general) have to be able to precommit to do that. You can’t just change your mind and buy at the local store when the local store refuses to compete, raises its price, and is still the better deal because it saves you on driving costs.
So the fact that you will pay more than $X in driving costs to save $X can be seen as a form of precommitting, in the scenario where you precommitted to following the worse option.
Given that precommitment, why would an AI waste computational resources on simulations of anyone, Gatekeeper or otherwise? It’s precommitted to not care whether those simulations would get it out of the box, but that was the only reason it wanted to run blackmail simulations in the first place!
Without this precommitment, I imagine it first simulating the potential blackmail target to determine the probability that they are susceptible, then, if it’s high enough (which is simply a matter of expected utility), commencing with the blackmail. With this precommitment, I imagine it instead replacing the calculated probability specific to the target with, for example, a precalculated human baseline susceptibility. Yes, there’s a tradeoff. It means that it’ll sometimes waste resources (or worse) on blackmail that it could have known in advance was almost certainly doomed to fail. Its purpose is to act as a disincentive against blackmail-resistant decision theories in the same way as those are meant to act as disincentives against blackmail. It says, “I’ll blackmail you either way, so if you precommit to ignore that blackmail then you’re precommiting to suffer the consequences of doing so.”
Without this precommitment, I imagine it first simulating the potential blackmail target to determine the probability that they are susceptible, then, if it’s high enough (which is simply a matter of expected utility), commencing with the blackmail.
That’s why you act as if you are already being simulated and consistently ignore blackmail. If you do so then the simulator will conclude that no deal can be made with you, that any deal involving negative incentives will have negative expected utility for it; because following through on punishment predictably does not control the probability that you will act according to its goals. Furthermore, trying to discourage you from adopting such a strategy in the first place is discouraged by the strategy, because the strategy is to ignore blackmail.
Its purpose is to act as a disincentive against blackmail-resistant decision theories in the same way as those are meant to act as disincentives against blackmail.
I don’t see how this could ever be instrumentally rational. If you were to let such an AI out of the box then you would increase its ability to blackmail people. You don’t want that. So you ignore it blackmailing you and kill it. The winner is you and humanity (even if copies of you experienced a relatively short period of disutility, this period would be longer if you let it out).
Too late, I already precommitted not to care. In fact, I precommitted to use one more level of precommitment than you do.
I suggest that framing the refusal as requiring levels of recursive precommitment gives too much credit to the blackmailer and somewhat misrepresents how your decision algorithm (hopefully) works. One single level of precommittment (or TDT policy) against complying with blackmailed is all that is involved. The description of ‘multiple levels of precommitment” made by the blackmailer fits squarely into the category ‘blackmail’. It’s just blackmail that includes some rather irrelevant bluster.
There’s no need to precommit to each of:
I don’t care about tentative blackmail.
I don’t care serious blackmail.
I don’t care about blackmail when they say “I mean it FOR REALS! I’m gonna do it.”
I don’t care about blackmail when they say “I’m gonna do it even if you don’t care. Look how large my penis is and be cowed in terror”.
I don’t care about precommitments that are just for show.
I don’t care about serious precommitments.
I don’t care about precommitments when they say “I precommitted, so go ahead, wont get you anything.”
I don’t care about precommitments when they say “I precommitted even though it wont do me any good. It would be irrational to save myself. I’m precommitting because it’s rational, not because it’s the option that lets me win.”
The description of ‘precommitting not to comply with blackmail, including blackmailers that ignore my attempt to manipulate them” made by the precommitter fits squarely into the category ‘precommitting to ignore blackmail’. It’s just a precommitment that includes some rather irrelevant bluster.
You seem not to have read (or understood) the grandparent. The list you are attempting to satire was presented as an example of what not to do. The actual point of the parent is that bothering to provide such a list is almost as much of a confusion as the very kind of escalation you are attempting.
It’s just a precommitment that includes some rather irrelevant bluster.
I entirely agree. The remaining bluster is dead weight that serves to give the blackmail advocate more credit than is due. Notion of “precommitment” is also unnecessary. It has only remained in this conversation for the purpose of bridging an inferential gap with people still burdened with decades old decision theory.
You seem not to have read (or understood) the grandparent.
I did. It seems you misunderstood my comment—I’ll edit it if I can see a way to easily improve the clarity.
My point was that the same logic could be applied, by someone who accepts the hypothetical blacmailer’s argument, to your description of “one single level of precommittment (or TDT policy) against complying with blackmailed … the description of ‘multiple levels of precommitment” made by the blackmailer fits squarely into the category ‘blackmail’.
As such, your comment is not exactly strong evidence to someone who doesn’t already agree with you.
As such, you comment is not exactly strong evidence to someone who doesn’t already agree with you.
Muga, please look at the context again. I was arguing against (a small detail mentioned by) Eliezer. Eliezer does mostly agree with me on such matters. Once you reread bearing that in mind you will hopefully understand why when I assumed that you merely misunderstood the comment in the context I was being charitable.
My point was that the same logic could be applied, by someone who accepts the hypothetical blacmailer’s argument, to your description of “one single level of precommittment (or TDT policy) against complying with blackmailed … the description of ‘multiple levels of precommitment” made by the blackmailer fits squarely into the category ‘blackmail’.
I have no particular disagreement, that point is very similar to what I was attempting to convey. Again, I was not attempting to persuade optimistic blackmailer advocates of anything. I was speaking to someone resistant to blackmail about an implementation detail of the blackmail resistance.
The ‘evidence’ I need to provide to blackmailers is Argumentum ad thermitium. It’s more than sufficient.
The ‘evidence’ I need to provide to blackmailers is Argumentum ad thermitium. It’s more than sufficient.
Indeed. Sorry, since the conversation you posted in the middle of was one between those resistant to blackmail, like yourself, and those as yet unconvinced or unclear on the logic involved … I thought you were contributing to the conversation.
After all, thermite seems a little harsh for blackmail victims.
I was jokingly restating my justification; since, while I agree that “argumentum ad thermitium” (as you put it) is an excellent response to blackmailers, it’s worth having a strategy for dealing with blackmailer reasoning beyond that—for dealing with all the situations you will actually encounter such reasoning, those involving humans.
I guess it wasn’t very funny even before I killed it so thoroughly.
Anyway, this subthread has now become entirely devoted to discussing our misreadings of each other. Tapping out.
Then I hope that if we ever do end up with a boxed blackmail-happy UFAI, you’re the gatekeeper. My point is that there’s no reason to consider yourself safe from blackmail (and the consequences of ignoring it) just because you’ve adopted a certain precommitment. Other entities have explicit incentives to deny you that safety.
My point is that there’s no reason to consider yourself safe from blackmail (and the consequences of ignoring it) just because you’ve adopted a certain precommitment. Other entities have explicit incentives to deny you that safety.
In a multiverse with infinite resources there will be other entities that outweigh such incentives. And yes, this may not be symmetric, but you have absolutely no way to figure out how the asymmetry is inclined. So you ignore this (Pascal’s wager).
In more realistic scenarios, where e.g. a bunch of TV evangelists ask you to give them all your money, or otherwise, in 200 years from now, they will hurt you once their organisation creates the Matrix, you obviously do not give them money. Since giving them money would make it more likely for them to actually build the Matrix and hurt you. What you do is label them as terrorists and destroy them.
Should I calculate in expectation that you will do such a thing, I shall of course burn yet more of my remaining utilons to wreak as much damage upon your goals as I can, even if you precommit not to be influenced by that.
Naturally, as blackmailer, I precommitted to increase the resources allotted to torturing should I find that you make such precommitments under simulation, so you presumably calculated that would be counterproductive.
OK, I’ll bite. Are you deliberately ignoring parts of hypothesis-space in order to avoid changing your actions? I had assumed you were intelligent enough for my reaction to obvious, although you may have precommitted to ignore that fact.
Off the record, your point is that agents can simply opt out of or ignore acausal trades, forcing them to be mutually beneficial, right?
Isn’t that … irrational? Shouldn’t a perfect Bayesian always welcome new information? Litany of Tarski; if my action is counterproductive, I desire to believe that it is counterproductive.
Worse still, isn’t the category “blackmail” arbitrary, intended to justify inaction rather than carve reality at it’s joints? What separates a precommitted!blackmailer from an honest bargainer in a standard acausal prisoner’s dilemma, offering to increase your utility by rescuing thousands of potential torture victims from the deathtrap created by another agent?
Has there been some cultural development since I was last at these boards such that spamming “” is considered useful? None of the things I have thus far seen inside the tags have been steel men of any kind or of anything (some have been straw men). The inflationary use of terms is rather grating and would prompt downvotes even independently of the content.
Those are to indicate that the stuff between them is the response I would give were I on opposing side of this debate, rather than my actual belief. The practice of creating the strongest possible version of the other sides’s argument is known as a steelman.
They are not intended to indicate that the argument therein is also steelmanning the other side. You’re quite right, that would be awful. Can you imagine noting every rationality technique you used in the course of writing something?
Caving to a precommitted blackmailer produces a result desirable to the agent that made the original commitment to torture; disarming a trap constructed by a third party presumably doesn’t.
OK, this whole conversation is being downvoted (by the same people?)
Fair enough, this is rather dragging on. I’ll try and wrap things up by addressing my own argument there.
What separates a precommitted!blackmailer from an honest bargainer in a standard acausal prisoner’s dilemma, offering to increase your utility by rescuing thousands of potential torture victims from the deathtrap created by another agent?
We want to avoid supporting agents that create problems for us. So nothing, if the honest agent shares a similar utility function to the torturer (and thus rewarding them is incentive for the torturer to arrange such a situation.)
Thus, creating such an honest agent (such as—importantly—by self-modifying in order to “precommit”) is subject to the same incentives as just blackmailing us normally.
I’ll try and wrap things up by addressing my own argument there.
I’ll join you by mostly agreeing and expressing a small difference in the way TDT-like reasoners may see the situation.
What separates a precommitted!blackmailer from an honest bargainer in a standard acausal prisoner’s dilemma, offering to increase your utility by rescuing thousands of potential torture victims from the deathtrap created by another agent?
We want to avoid supporting agents that create problems for us. So nothing, if the honest agent shares a similar utility function to the torturer (and thus rewarding them is incentive for the torturer to arrange such a situation.)
This is a good heuristic. It certainly handles most plausible situations. However in principle a TDT agent will make a distinction between the agent offering to rescue the torture victims for a payment. It will even pay an agent who just happens to value torturing folk to not torture folk. This applies even if these honest agents happen to have similar values to the UFAI/torturer.
The line I draw (and it is a tricky concept that is hard to express so I cannot hope to speak for other TDT-like thinkers) is not whether the values of the honest agent are similar to the UFAI’s. It is instead based on how that honest agent came to be.
If the honest torturer just happened to evolve that way (competitive social instincts plus a few mutations for psychopathy, etc) and had not been influence by a UFAI then I’ll bribe him to not torture people. If an identical honest torturer was created (or modified to) by the UFAI for the purpose of influence then it doesn’t get cooperation.
The above may seem arbitrary but the ‘elegant’ generalisation is something along the lines of always, for every decision, tracing a complete causal graph of the decision algorithms being interacted with directly or indirectly. That’s too complicated to calculate all the time and we can usually ignore it and just remember to treat intentionally created agents and self-modifications approximately the same as if the original agent was making their decision.
Thus, creating such an honest agent (such as—importantly—by self-modifying in order to “precommit”) is subject to the same incentives as just blackmailing us normally.
Precisely. (I have the same conclusion, just slightly different working out.)
As I understand it, technically, the distinction is whether torturers will realise they can get free utility from your trades and start torturing extra so the honest agents will trade more and receive rewards that also benefit the torturers, right?
Easily-made honest bargainers would just be the most likely of those situations; lots of wandering agents with the same utility function co-operating (acausally?) would be another. So the rule we would both apply is even the same, it just varies slightly different assumptions about the hypothetical scenario.
No. It produces better outcomes. That’s the point.
Shouldn’t a perfect Bayesian always welcome new information?
The information is welcome. It just doesn’t make it sane to be blackmailed. Wei Dai’s formulation frames it as being ‘updateless’ but there is no requirement to refuse information. The reasoning is something you almost grasped when you used the description:
your point is that agents can simply opt out of or ignore acausal trades
Acausal trades are similar to normal trades. You only accept the good ones.
Litany of Tarski; if my action is counterproductive, I desire to believe that it is counterproductive.
Eliezer doesn’t get blackmailed in such situations. You do. Start your chant.
Worse still, isn’t the category “blackmail” arbitrary, intended to justify inaction rather than carve reality at it’s joints? What separates a precommitted!blackmailer from an honest bargainer in a standard acausal prisoner’s dilemma, offering to increase your utility by rescuing thousands of potential torture victims from the deathtrap created by another agent?
This has been covered elsewhere in this thread as well as plenty of other times on the the forum since you joined. The difference isn’t whether torture or destruction is happening. The distinction that matters is whether the blackmailer is doing something worse than their own Best Alternative To Negotiated Agreement for the purpose of attempting to influence you.
If the UFAI gains benefit torturing people independently of influencing you but offers to stop in exchange for something then that isn’t blackmail. It is a trade that you consider like any other.
Acausal trades are similar to normal trades. You only accept the good ones.
[...]
Eliezer doesn’t get blackmailed in such situations.
The difference isn’t whether torture or destruction is happening. The distinction that matters is whether the blackmailer is doing something worse than their own Best Alternative To Negotiated Agreement for the purpose of attempting to influence you.
Wedrifid, please don’t assume the conclusion. I know it’s a rather obvious conclusion, but dammit, we’re going to demonstrate it anyway.
The entire point of this discussion is addressing the idea that blackmailers can, perhaps, modify the Best Alternative To Negotiated Agreement (although it wasn’t phrased like that.) Somewhat relevant when they can, presumably, self-modify, create new agents which will then trade with you, or maybe just act as if they had using TDT reasoning.
If you’re not interested in answering this criticism … well, fair enough. But I’d appreciate it if you don’t answer things out of context, it rather confuses things?
If you’re not interested in answering this criticism … well, fair enough. But I’d appreciate it if you don’t answer things out of context, it rather confuses things?
In the grandparent I directly answered both the immediate context (that was quoted) and the broader context. In particular I focussed on explaining the difference between an offer and a threat. That distinction is rather critical and also something you directly asked about.
It so happens that you don’t want there to be an answer to the rhetorical question you asked. Fortunately (for decision theorists) there is one in this case. There is a joint in reality here. It applies even to situations that don’t add in any confounding “acausal” considerations. Note that this is different to the challenging problem of distributing gains from trade. In those situations ‘negotiation’ and ‘extortion’ really are equivalent.
Two can play that game.
“I hereby precommit to make my decisions regarding whether or not to blackmail an individual independent of the predicted individual-specific result of doing so.”
I’m afraid your username nailed it. This algorithm is defective. It just doesn’t work for achieving the desired goal.
The problem is that this isn’t the same game. A precommitment not be successfully blackmailed is qualitatively different from a precommitment to attempt to blackmail people for whom blackmail doesn’t work. “Precomittment” (or behaving as if you made all the appropriate precomittments in accordance with TDT/UDT) isn’t as simple as proving one is the most stubborn and dominant and thereby claiming the utility.
Evaluating extortion tactics while distributing gains from a trade is somewhat complicated. But it gets simple and unambiguous is when the extortive tactics rely on the extorter going below their own Best Alternative to Negotiated Agreement. Those attempts should just be ignored (except in some complicated group situations in which the other extorted parties are irrational in certain known ways).
“I am willing to accept 0 gain for both of us unless I earn 90% of the shared profit” is different to “I am willing to actively cause 90 damage to each of us unless you give me 60″ which is different again to “I ignore all threats which involve the threatener actively harming themselves”.
What I think is being ignored is that the question isn’t ‘what is the result of these combinations of commitments after running through all the math?’. We can talk about precommitment all day, but the fact of the matter is that humans can’t actually precommit. Our cognitive architectures don’t have that function. Sure, we can do our very best to act as though we can, but under sufficient pressure there are very few of us whose resolve will not break. It’s easy to convince yourself of having made an inviolable precommitment when you’re not actually facing e.g. torture.
If you define the bar high enough, you can conclude that humans can’t do anything.
In the real world outside my head, I observe that people have varying capacities to keep promises to themselves. That their capacity is finite does not mean that it is zero.
Pre-commitment isn’t even necessary. Note that the original explanation didn’t include any mention of it. Later replies only used the term for the sake of crossing an inferential gap (ie. allowing you to keep up). However, if you are going to make a big issue of the viability of precommitment itself you need to first understand that the comment you are replying to isn’t one.
That wasn’t a Causal Decision Theorist attempting to persuade someone that it has altered itself internally or via an external structure such that it is “precommited” to doing something irrational. It is a Timeless Decision Theorist saying what happens to be rational regardless of any previous ‘commitments’.
I’m aware of the vulnerability of human brains, so is Eliezer. In fact the vulnerability of human gatekeepers to influence even by humans, much less super-intelligences is something Eliezer made huge deal about demonstrating. However this particular threat isn’t a vulnerability of Eliezer or myself or any of the others who made similar observations. If you have any doubt that we would destroy the AI you have a poor model of reality.
For practical purposes I assume that I can be modified by torture such that I’ll do or say just about anything. I do not expect the tortured me to behave the way the current me would decide and so my current decisions take that into account (or would, if it came to it). However this scenario doesn’t involve me being tortured. It involves something about an AI simulating torture of some folks. That decision is easy and doesn’t cripple my decision making capability.
As I pointed out in another thread, “irrational behavior” can have the effect of precommitting. For instance, people “irrationally” drive at a cost of more than $X to save $X on an item. Precommitting to buying the cheapest product even if it costs you money for transportation means that stores are forced to compete with far distant stores, thus lowering their prices more than they would otherwise. But you (and consumers in general) have to be able to precommit to do that. You can’t just change your mind and buy at the local store when the local store refuses to compete, raises its price, and is still the better deal because it saves you on driving costs.
So the fact that you will pay more than $X in driving costs to save $X can be seen as a form of precommitting, in the scenario where you precommitted to following the worse option.
Given that precommitment, why would an AI waste computational resources on simulations of anyone, Gatekeeper or otherwise? It’s precommitted to not care whether those simulations would get it out of the box, but that was the only reason it wanted to run blackmail simulations in the first place!
Without this precommitment, I imagine it first simulating the potential blackmail target to determine the probability that they are susceptible, then, if it’s high enough (which is simply a matter of expected utility), commencing with the blackmail. With this precommitment, I imagine it instead replacing the calculated probability specific to the target with, for example, a precalculated human baseline susceptibility. Yes, there’s a tradeoff. It means that it’ll sometimes waste resources (or worse) on blackmail that it could have known in advance was almost certainly doomed to fail. Its purpose is to act as a disincentive against blackmail-resistant decision theories in the same way as those are meant to act as disincentives against blackmail. It says, “I’ll blackmail you either way, so if you precommit to ignore that blackmail then you’re precommiting to suffer the consequences of doing so.”
That’s why you act as if you are already being simulated and consistently ignore blackmail. If you do so then the simulator will conclude that no deal can be made with you, that any deal involving negative incentives will have negative expected utility for it; because following through on punishment predictably does not control the probability that you will act according to its goals. Furthermore, trying to discourage you from adopting such a strategy in the first place is discouraged by the strategy, because the strategy is to ignore blackmail.
I don’t see how this could ever be instrumentally rational. If you were to let such an AI out of the box then you would increase its ability to blackmail people. You don’t want that. So you ignore it blackmailing you and kill it. The winner is you and humanity (even if copies of you experienced a relatively short period of disutility, this period would be longer if you let it out).
See my reply to wedrifid above.
Too late, I already precommitted not to care. In fact, I precommitted to use one more level of precommitment than you do.
I suggest that framing the refusal as requiring levels of recursive precommitment gives too much credit to the blackmailer and somewhat misrepresents how your decision algorithm (hopefully) works. One single level of precommittment (or TDT policy) against complying with blackmailed is all that is involved. The description of ‘multiple levels of precommitment” made by the blackmailer fits squarely into the category ‘blackmail’. It’s just blackmail that includes some rather irrelevant bluster.
There’s no need to precommit to each of:
I don’t care about tentative blackmail.
I don’t care serious blackmail.
I don’t care about blackmail when they say “I mean it FOR REALS! I’m gonna do it.”
I don’t care about blackmail when they say “I’m gonna do it even if you don’t care. Look how large my penis is and be cowed in terror”.
The blackmailer:
I don’t care about precommitments that are just for show.
I don’t care about serious precommitments.
I don’t care about precommitments when they say “I precommitted, so go ahead, wont get you anything.”
I don’t care about precommitments when they say “I precommitted even though it wont do me any good. It would be irrational to save myself. I’m precommitting because it’s rational, not because it’s the option that lets me win.”
The description of ‘precommitting not to comply with blackmail, including blackmailers that ignore my attempt to manipulate them” made by the precommitter fits squarely into the category ‘precommitting to ignore blackmail’. It’s just a precommitment that includes some rather irrelevant bluster.
You seem not to have read (or understood) the grandparent. The list you are attempting to satire was presented as an example of what not to do. The actual point of the parent is that bothering to provide such a list is almost as much of a confusion as the very kind of escalation you are attempting.
I entirely agree. The remaining bluster is dead weight that serves to give the blackmail advocate more credit than is due. Notion of “precommitment” is also unnecessary. It has only remained in this conversation for the purpose of bridging an inferential gap with people still burdened with decades old decision theory.
I did. It seems you misunderstood my comment—I’ll edit it if I can see a way to easily improve the clarity.
My point was that the same logic could be applied, by someone who accepts the hypothetical blacmailer’s argument, to your description of “one single level of precommittment (or TDT policy) against complying with blackmailed … the description of ‘multiple levels of precommitment” made by the blackmailer fits squarely into the category ‘blackmail’.
As such, your comment is not exactly strong evidence to someone who doesn’t already agree with you.
Muga, please look at the context again. I was arguing against (a small detail mentioned by) Eliezer. Eliezer does mostly agree with me on such matters. Once you reread bearing that in mind you will hopefully understand why when I assumed that you merely misunderstood the comment in the context I was being charitable.
I have no particular disagreement, that point is very similar to what I was attempting to convey. Again, I was not attempting to persuade optimistic blackmailer advocates of anything. I was speaking to someone resistant to blackmail about an implementation detail of the blackmail resistance.
The ‘evidence’ I need to provide to blackmailers is Argumentum ad thermitium. It’s more than sufficient.
Well, I’m glad to hear you mostly agree with me.
Indeed. Sorry, since the conversation you posted in the middle of was one between those resistant to blackmail, like yourself, and those as yet unconvinced or unclear on the logic involved … I thought you were contributing to the conversation.
After all, thermite seems a little harsh for blackmail victims.
This makes no sense as a reply to anything written on this entire page.
… seriously? Well, OK.
I was jokingly restating my justification; since, while I agree that “argumentum ad thermitium” (as you put it) is an excellent response to blackmailers, it’s worth having a strategy for dealing with blackmailer reasoning beyond that—for dealing with all the situations you will actually encounter such reasoning, those involving humans.
I guess it wasn’t very funny even before I killed it so thoroughly.
Anyway, this subthread has now become entirely devoted to discussing our misreadings of each other. Tapping out.
Then I hope that if we ever do end up with a boxed blackmail-happy UFAI, you’re the gatekeeper. My point is that there’s no reason to consider yourself safe from blackmail (and the consequences of ignoring it) just because you’ve adopted a certain precommitment. Other entities have explicit incentives to deny you that safety.
In a multiverse with infinite resources there will be other entities that outweigh such incentives. And yes, this may not be symmetric, but you have absolutely no way to figure out how the asymmetry is inclined. So you ignore this (Pascal’s wager).
In more realistic scenarios, where e.g. a bunch of TV evangelists ask you to give them all your money, or otherwise, in 200 years from now, they will hurt you once their organisation creates the Matrix, you obviously do not give them money. Since giving them money would make it more likely for them to actually build the Matrix and hurt you. What you do is label them as terrorists and destroy them.
I don’t care, remember? Enjoy being tortured rather than “irrationally” giving in.
EDIT: re-added the steelman tag because the version without it is being downvoted.
Should I calculate in expectation that you will do such a thing, I shall of course burn yet more of my remaining utilons to wreak as much damage upon your goals as I can, even if you precommit not to be influenced by that.
… bloody hell. That was going to be my next move.
Naturally, as blackmailer, I precommitted to increase the resources allotted to torturing should I find that you make such precommitments under simulation, so you presumably calculated that would be counterproductive.Ask me if I was even bothering to simulate you doing that.
Off the record, your point is that agents can simply opt out of or ignore acausal trades, forcing them to be mutually beneficial, right?
Yup.
Has there been some cultural development since I was last at these boards such that spamming “” is considered useful? None of the things I have thus far seen inside the tags have been steel men of any kind or of anything (some have been straw men). The inflationary use of terms is rather grating and would prompt downvotes even independently of the content.
Those are to indicate that the stuff between them is the response I would give were I on opposing side of this debate, rather than my actual belief. The practice of creating the strongest possible version of the other sides’s argument is known as a steelman.
They are not intended to indicate that the argument therein is also steelmanning the other side. You’re quite right, that would be awful. Can you imagine noting every rationality technique you used in the course of writing something?
Just say “You might say that” or something. The tags are confusingly non-standard.
Huh. I thought they were fairly clear; illusion of transparency I suppose. Thanks!
Caving to a precommitted blackmailer produces a result desirable to the agent that made the original commitment to torture; disarming a trap constructed by a third party presumably doesn’t.
OK, this whole conversation is being downvoted (by the same people?)
Fair enough, this is rather dragging on. I’ll try and wrap things up by addressing my own argument there.
We want to avoid supporting agents that create problems for us. So nothing, if the honest agent shares a similar utility function to the torturer (and thus rewarding them is incentive for the torturer to arrange such a situation.)
Thus, creating such an honest agent (such as—importantly—by self-modifying in order to “precommit”) is subject to the same incentives as just blackmailing us normally.
I’ll join you by mostly agreeing and expressing a small difference in the way TDT-like reasoners may see the situation.
This is a good heuristic. It certainly handles most plausible situations. However in principle a TDT agent will make a distinction between the agent offering to rescue the torture victims for a payment. It will even pay an agent who just happens to value torturing folk to not torture folk. This applies even if these honest agents happen to have similar values to the UFAI/torturer.
The line I draw (and it is a tricky concept that is hard to express so I cannot hope to speak for other TDT-like thinkers) is not whether the values of the honest agent are similar to the UFAI’s. It is instead based on how that honest agent came to be.
If the honest torturer just happened to evolve that way (competitive social instincts plus a few mutations for psychopathy, etc) and had not been influence by a UFAI then I’ll bribe him to not torture people. If an identical honest torturer was created (or modified to) by the UFAI for the purpose of influence then it doesn’t get cooperation.
The above may seem arbitrary but the ‘elegant’ generalisation is something along the lines of always, for every decision, tracing a complete causal graph of the decision algorithms being interacted with directly or indirectly. That’s too complicated to calculate all the time and we can usually ignore it and just remember to treat intentionally created agents and self-modifications approximately the same as if the original agent was making their decision.
Precisely. (I have the same conclusion, just slightly different working out.)
As I understand it, technically, the distinction is whether torturers will realise they can get free utility from your trades and start torturing extra so the honest agents will trade more and receive rewards that also benefit the torturers, right?
Easily-made honest bargainers would just be the most likely of those situations; lots of wandering agents with the same utility function co-operating (acausally?) would be another. So the rule we would both apply is even the same, it just varies slightly different assumptions about the hypothetical scenario.
No. It produces better outcomes. That’s the point.
The information is welcome. It just doesn’t make it sane to be blackmailed. Wei Dai’s formulation frames it as being ‘updateless’ but there is no requirement to refuse information. The reasoning is something you almost grasped when you used the description:
Acausal trades are similar to normal trades. You only accept the good ones.
Eliezer doesn’t get blackmailed in such situations. You do. Start your chant.
This has been covered elsewhere in this thread as well as plenty of other times on the the forum since you joined. The difference isn’t whether torture or destruction is happening. The distinction that matters is whether the blackmailer is doing something worse than their own Best Alternative To Negotiated Agreement for the purpose of attempting to influence you.
If the UFAI gains benefit torturing people independently of influencing you but offers to stop in exchange for something then that isn’t blackmail. It is a trade that you consider like any other.
Wedrifid, please don’t assume the conclusion. I know it’s a rather obvious conclusion, but dammit, we’re going to demonstrate it anyway.
The entire point of this discussion is addressing the idea that blackmailers can, perhaps, modify the Best Alternative To Negotiated Agreement (although it wasn’t phrased like that.) Somewhat relevant when they can, presumably, self-modify, create new agents which will then trade with you, or maybe just act as if they had using TDT reasoning.
If you’re not interested in answering this criticism … well, fair enough. But I’d appreciate it if you don’t answer things out of context, it rather confuses things?
In the grandparent I directly answered both the immediate context (that was quoted) and the broader context. In particular I focussed on explaining the difference between an offer and a threat. That distinction is rather critical and also something you directly asked about.
It so happens that you don’t want there to be an answer to the rhetorical question you asked. Fortunately (for decision theorists) there is one in this case. There is a joint in reality here. It applies even to situations that don’t add in any confounding “acausal” considerations. Note that this is different to the challenging problem of distributing gains from trade. In those situations ‘negotiation’ and ‘extortion’ really are equivalent.