The post makes the important argument that if we have a word whose boundary is around a pretty important set of phenomena that are useful to have a quick handle to refer to, then
It’s really unhelpful for people to start using the word to also refer to a phenomena with 10x or 100x more occurrences in the world because then I’m no longer able to point to the specific important parts of the phenomena that I was previously talking about
e.g. Currently the word ‘abuser’ describes a small number of people during some of their lives. Someone might want to say that technically it should refer to all people all of the time. The argument is understandable, but it wholly destroys the usefulness of the concept handle.
People often have political incentives to push the concept boundary to include a specific case in a way that, if it were principled, indeed makes most of the phenomena in the category no use to talk about. This allows for selective policing being the people with the political incentive.
It’s often fine for people to bend words a little bit (e.g. when people verb nouns), but when it’s in the class of terms we use for norm violation, it’s often correct to impose quite high standards of evidence for doing so, as we can have strong incentives (and unconscious biases!) to do it for political reasons.
These are key points that argue against changing the concept boundary to include all conscious reporting of unconscious bias, and more generally push back against unprincipled additions to the concept boundary.
This is not an argument against expanding the concept to include a specific set of phenomena that share the key similarities with the original set, as long as the expansion does not explode the set. I think there may be some things like that within the category of ‘unconscious bias’.
While it is the case that it’s very helpful to have a word for when a human consciously deceives another human, my sense is that there are some important edge cases that we would still call lying, or at least a severe breach of integrity that should be treated similarly to deliberate conscious lies.
Humans are incentivised to self-deceive in the social domain in order to be able to tell convincing lies. It’s sometimes important that if it’s found out that someone strategically self-deceived, that they be punished in some way.
A central example here might be a guy who says he wants to be in a long and loving committed relationship, only to break up after he is bored of the sex after 6-12 months, and really this was predictable from the start if he hadn’t felt it was fine to make big commitments things without introspecting carefully on their truth. I can imagine the woman in this scenario feeling genuinely shocked and lied to. “Hold on, what are you talking about that you feel you want to move out? I am organising my whole life around this relationship, what you are doing right now is calling into question the basic assumptions that you have promised to me.” I can imagine this guy getting a reputation for being untrustworthy and lying to women. I think it is an open question about whether it is accurate for the woman cheated by this man to tell other people that he “lied to her”, though I think it is plausible that I want to punish this behaviour in a similar way that I want to punish much more conscious deception, in a way that motivates me to want to refer to it with the same handle—because it gives you basically very similar operational beliefs about the situation (the person systematically deceived me in a way that was clearly for their personal gain and this hurt me and I think they should be actively punished).
I think I can probably come up with an example where a politician wants power and does whatever is required to take it, such that they end up not being in alignment with the values they stated they held earlier in their career, and allow the meaning of words to fluctuate around them in accordance with what the people giving the politician votes and power want that they end up saying something that is effectively a lie, but that they don’t care about or really notice. This one is a bit slippery for me to point to.
Another context that is relevant: I can imagine going to a scientific conference in a field that has been hit so hard by the replication crisis, that basically all the claims in the conference were false, and I could know this. Not only are the claims at this conference false, but the whole subfield has never been about anything real (example, example, and of course, example). I can imagine a friend of mine attending such a conference and talking to me afterwards, and them thinking that some of the claims seemed true. And I can imagine saying to them “No. You need to understand that all the claims in there are lies. There is no truth-tracking process occurring. It is a sham field, and those people should not be getting funding for their research.” Now, do I think the individuals in the field are immoral? Not exactly, but sorta. They didn’t care about truth and yet paraded themselves as scientists. But I guess that’s a big enough thing in society that they weren’t unusually bad or anything. While it’s not a central case of lying, it currently feels to me like it’s actively helpful for me to use the phrase ‘lie’ and ‘sham’. There is a systematic distortion of truth that gives people resources they want instead of those resources going to projects not systematically distorting reality.
(ADDED: OTOH I do think that I have myself in the past been prompted to want to punish people for these kinds of ‘lies’ in ways that isn’t effective. I have felt that people who have committed severe breaches of integrity in the communities I’m part of are bad people and felt very angry at them, but I think that this has often been an inappropriate response. It does share other important similarities with lies though. Probably want to be a bit careful with the usage here and signal that the part of wanting to immediately socially punish them for a thing that they obviously did wrong is not helpful, because they will feel helpless and not that it’s obvious they did something wrong. But it’s important for me internally to model them as something close to lying, for the sanity of my epistemic state, especially when many people in my environment will not know/think the person has breached integrity and will socially encourage me to positively weight their opinions/statements.)
My current guess at the truth: there are classes of human motivations, such as those for sex, and for prestigious employment positions in the modern world, that have sufficiently systematic biases in favour of self-deception that it is not damaging to add them to the category of ‘lie’ - adding them is not the same as a rule that admits all unconscious bias consciously reported, just a subset that reliably turns up again and again. I think Jessica Taylor / Ben Hoffman / Michael Arc want to use the word ‘fraud’ to refer to it, I’m not sure.
I will actually clean this up and into a post sometime soon [edit: I retract that, I am not able to make commitments like this right now]. For now let me add another quick hypothesis on this topic whilst crashing from jet lag.
A friend of mine proposed that instead of saying ‘lies’ I could say ‘falsehoods’. Not “that claim is a lie” but “that claim is false”.
I responded that ‘falsehood’ doesn’t capture the fact that you should expect systematic deviations from the truth. I’m not saying this particular parapsychology claim is false. I’m saying it is false in a way where you should no longer trust the other claims, and expect they’ve been optimised to be persuasive.
They gave another proposal, which is to say instead of “they’re lying” to say “they’re not truth-tracking”. Suggest that their reasoning process (perhaps in one particular domain) does not track truth.
I responded that while this was better, it still seems to me that people won’t have an informal understanding of how to use this information. (Are you saying that the ideas aren’t especially well-evidenced? But they sound pretty plausible to me, so let’s keep discussing them and look for more evidence.) There’s a thing where if you say someone is a liar, not only do you not trust them, but you recognise that you shouldn’t even privilege the hypotheses that they produce. If there’s no strong evidence either way, if it turns out the person who told it you is a rotten liar, then if you wouldn’t have considered it before they raised it, don’t consider it now.
Then I realised Jacob had written about this topic a few months back. People talk as though ‘responding to economic incentives’ requires conscious motivation, but actually there are lots of ways that incentives cause things to happen that don’t require humans consciously noticing the incentives and deliberately changing their behaviour. Selection effects, reinforcement learning, and memetic evolution.
Similarly, what I’m looking for is basic terminology for pointing to processes that systematically produce persuasive things that aren’t true, that doesn’t move through “this person is consciously deceiving me”. The scientists pushing adult neurogenesis aren’t lying. There’s a different force happening here that we need to learn to give epistemic weight to the same way we treat a liar, but without expecting conscious motivation to be the root of the force and thus trying to treat it that way (e.g. by social punishment).
More broadly, it seems like there are persuasive systems in the environment that weren’t in the evolutionary environment for adaptation, that we have not collectively learned to model clearly. Perhaps we should invest in some basic terminology that points to these systems so we can learn to not-trust them without bringing in social punishment norms.
The definitional boundaries of “abuser,” as Scott notes, are in large part about coordinating around whom to censure. The definition is pragmatic rather than objective.*
If the motive for the definition of “lies” is similar, then a proposal to define only conscious deception as lying is therefore a proposal to censure people who defend themselves against coercion while privately maintaining coherent beliefs, but not those who defend themselves against coercion by simply failing to maintain coherent beliefs in the first place. (For more on this, see Nightmare of the Perfectly Principled.) This amounts to waging war against the mind.
Of course, in matter of actual fact we don’t strongly censure all cases of consciously deceiving. In some cases (e.g. “white lies”) we punish those who fail to lie, and those who call out the lie. I’m also pretty sure we don’t actually distinguish between conscious deception and e.g. reflexively saying an expedient thing, when it’s abundantly clear that one knows very well that the expedient thing to say is false, as Jessica pointed out here.
*It’s not clear to me that this is a good kind of concept to have, even for “abuser.” It seems to systematically force responses to harmful behavior to bifurcate into “this is normal and fine” and “this person must be expelled from the tribe,” with little room for judgments like “this seems like an important thing for future partners to be warned about, but not relevant in other contexts.” This bifurcation makes me less willing to disclose adverse info about people publicly—there are prominent members of the Bay Area Rationalist community doing deeply shitty, harmful things that I actually don’t feel okay talking about beyond close friends because I expect people like Scott to try to enforce splitting behavior.
Note: I just wrote this in one pass when severely jet lagged, and did not have the effort to edit it much. If I end up turning this into a blogpost I will probably do that. Anyway, I am interested in hearing via PM from anyone who feels that it was sufficiently unclearly written that they had a hard time understanding/reading it.
Responding to Scott’s response to Jessica.
The post makes the important argument that if we have a word whose boundary is around a pretty important set of phenomena that are useful to have a quick handle to refer to, then
It’s really unhelpful for people to start using the word to also refer to a phenomena with 10x or 100x more occurrences in the world because then I’m no longer able to point to the specific important parts of the phenomena that I was previously talking about
e.g. Currently the word ‘abuser’ describes a small number of people during some of their lives. Someone might want to say that technically it should refer to all people all of the time. The argument is understandable, but it wholly destroys the usefulness of the concept handle.
People often have political incentives to push the concept boundary to include a specific case in a way that, if it were principled, indeed makes most of the phenomena in the category no use to talk about. This allows for selective policing being the people with the political incentive.
It’s often fine for people to bend words a little bit (e.g. when people verb nouns), but when it’s in the class of terms we use for norm violation, it’s often correct to impose quite high standards of evidence for doing so, as we can have strong incentives (and unconscious biases!) to do it for political reasons.
These are key points that argue against changing the concept boundary to include all conscious reporting of unconscious bias, and more generally push back against unprincipled additions to the concept boundary.
This is not an argument against expanding the concept to include a specific set of phenomena that share the key similarities with the original set, as long as the expansion does not explode the set. I think there may be some things like that within the category of ‘unconscious bias’.
While it is the case that it’s very helpful to have a word for when a human consciously deceives another human, my sense is that there are some important edge cases that we would still call lying, or at least a severe breach of integrity that should be treated similarly to deliberate conscious lies.
Humans are incentivised to self-deceive in the social domain in order to be able to tell convincing lies. It’s sometimes important that if it’s found out that someone strategically self-deceived, that they be punished in some way.
A central example here might be a guy who says he wants to be in a long and loving committed relationship, only to break up after he is bored of the sex after 6-12 months, and really this was predictable from the start if he hadn’t felt it was fine to make big commitments things without introspecting carefully on their truth. I can imagine the woman in this scenario feeling genuinely shocked and lied to. “Hold on, what are you talking about that you feel you want to move out? I am organising my whole life around this relationship, what you are doing right now is calling into question the basic assumptions that you have promised to me.” I can imagine this guy getting a reputation for being untrustworthy and lying to women. I think it is an open question about whether it is accurate for the woman cheated by this man to tell other people that he “lied to her”, though I think it is plausible that I want to punish this behaviour in a similar way that I want to punish much more conscious deception, in a way that motivates me to want to refer to it with the same handle—because it gives you basically very similar operational beliefs about the situation (the person systematically deceived me in a way that was clearly for their personal gain and this hurt me and I think they should be actively punished).
I think I can probably come up with an example where a politician wants power and does whatever is required to take it, such that they end up not being in alignment with the values they stated they held earlier in their career, and allow the meaning of words to fluctuate around them in accordance with what the people giving the politician votes and power want that they end up saying something that is effectively a lie, but that they don’t care about or really notice. This one is a bit slippery for me to point to.
Another context that is relevant: I can imagine going to a scientific conference in a field that has been hit so hard by the replication crisis, that basically all the claims in the conference were false, and I could know this. Not only are the claims at this conference false, but the whole subfield has never been about anything real (example, example, and of course, example). I can imagine a friend of mine attending such a conference and talking to me afterwards, and them thinking that some of the claims seemed true. And I can imagine saying to them “No. You need to understand that all the claims in there are lies. There is no truth-tracking process occurring. It is a sham field, and those people should not be getting funding for their research.” Now, do I think the individuals in the field are immoral? Not exactly, but sorta. They didn’t care about truth and yet paraded themselves as scientists. But I guess that’s a big enough thing in society that they weren’t unusually bad or anything. While it’s not a central case of lying, it currently feels to me like it’s actively helpful for me to use the phrase ‘lie’ and ‘sham’. There is a systematic distortion of truth that gives people resources they want instead of those resources going to projects not systematically distorting reality.
(ADDED: OTOH I do think that I have myself in the past been prompted to want to punish people for these kinds of ‘lies’ in ways that isn’t effective. I have felt that people who have committed severe breaches of integrity in the communities I’m part of are bad people and felt very angry at them, but I think that this has often been an inappropriate response. It does share other important similarities with lies though. Probably want to be a bit careful with the usage here and signal that the part of wanting to immediately socially punish them for a thing that they obviously did wrong is not helpful, because they will feel helpless and not that it’s obvious they did something wrong. But it’s important for me internally to model them as something close to lying, for the sanity of my epistemic state, especially when many people in my environment will not know/think the person has breached integrity and will socially encourage me to positively weight their opinions/statements.)
My current guess at the truth: there are classes of human motivations, such as those for sex, and for prestigious employment positions in the modern world, that have sufficiently systematic biases in favour of self-deception that it is not damaging to add them to the category of ‘lie’ - adding them is not the same as a rule that admits all unconscious bias consciously reported, just a subset that reliably turns up again and again. I think Jessica Taylor / Ben Hoffman / Michael Arc want to use the word ‘fraud’ to refer to it, I’m not sure.
I will actually clean this up and into a post sometime soon [edit: I retract that, I am not able to make commitments like this right now]. For now let me add another quick hypothesis on this topic whilst crashing from jet lag.
A friend of mine proposed that instead of saying ‘lies’ I could say ‘falsehoods’. Not “that claim is a lie” but “that claim is false”.
I responded that ‘falsehood’ doesn’t capture the fact that you should expect systematic deviations from the truth. I’m not saying this particular parapsychology claim is false. I’m saying it is false in a way where you should no longer trust the other claims, and expect they’ve been optimised to be persuasive.
They gave another proposal, which is to say instead of “they’re lying” to say “they’re not truth-tracking”. Suggest that their reasoning process (perhaps in one particular domain) does not track truth.
I responded that while this was better, it still seems to me that people won’t have an informal understanding of how to use this information. (Are you saying that the ideas aren’t especially well-evidenced? But they sound pretty plausible to me, so let’s keep discussing them and look for more evidence.) There’s a thing where if you say someone is a liar, not only do you not trust them, but you recognise that you shouldn’t even privilege the hypotheses that they produce. If there’s no strong evidence either way, if it turns out the person who told it you is a rotten liar, then if you wouldn’t have considered it before they raised it, don’t consider it now.
Then I realised Jacob had written about this topic a few months back. People talk as though ‘responding to economic incentives’ requires conscious motivation, but actually there are lots of ways that incentives cause things to happen that don’t require humans consciously noticing the incentives and deliberately changing their behaviour. Selection effects, reinforcement learning, and memetic evolution.
Similarly, what I’m looking for is basic terminology for pointing to processes that systematically produce persuasive things that aren’t true, that doesn’t move through “this person is consciously deceiving me”. The scientists pushing adult neurogenesis aren’t lying. There’s a different force happening here that we need to learn to give epistemic weight to the same way we treat a liar, but without expecting conscious motivation to be the root of the force and thus trying to treat it that way (e.g. by social punishment).
More broadly, it seems like there are persuasive systems in the environment that weren’t in the evolutionary environment for adaptation, that we have not collectively learned to model clearly. Perhaps we should invest in some basic terminology that points to these systems so we can learn to not-trust them without bringing in social punishment norms.
Is this “bias”?
Yeah good point I may have reinvented the wheel. I have a sense that’s not true but need to think more.
The definitional boundaries of “abuser,” as Scott notes, are in large part about coordinating around whom to censure. The definition is pragmatic rather than objective.*
If the motive for the definition of “lies” is similar, then a proposal to define only conscious deception as lying is therefore a proposal to censure people who defend themselves against coercion while privately maintaining coherent beliefs, but not those who defend themselves against coercion by simply failing to maintain coherent beliefs in the first place. (For more on this, see Nightmare of the Perfectly Principled.) This amounts to waging war against the mind.
Of course, in matter of actual fact we don’t strongly censure all cases of consciously deceiving. In some cases (e.g. “white lies”) we punish those who fail to lie, and those who call out the lie. I’m also pretty sure we don’t actually distinguish between conscious deception and e.g. reflexively saying an expedient thing, when it’s abundantly clear that one knows very well that the expedient thing to say is false, as Jessica pointed out here.
*It’s not clear to me that this is a good kind of concept to have, even for “abuser.” It seems to systematically force responses to harmful behavior to bifurcate into “this is normal and fine” and “this person must be expelled from the tribe,” with little room for judgments like “this seems like an important thing for future partners to be warned about, but not relevant in other contexts.” This bifurcation makes me less willing to disclose adverse info about people publicly—there are prominent members of the Bay Area Rationalist community doing deeply shitty, harmful things that I actually don’t feel okay talking about beyond close friends because I expect people like Scott to try to enforce splitting behavior.
Note: I just wrote this in one pass when severely jet lagged, and did not have the effort to edit it much. If I end up turning this into a blogpost I will probably do that. Anyway, I am interested in hearing via PM from anyone who feels that it was sufficiently unclearly written that they had a hard time understanding/reading it.