I am quite dismayed by Habryka’s words and ways and I hope he will reconsider them. LessWrong has been without doubt the greatest project for good to have appeared from the greater EA-sphere and indeed- the world. Having witnessed the birth of LW 2.0 I can say with some embarrassment that it was not at all clear that anything like LessWrong could have existed. It is a testimony to Habryka’s [and Ben Pace and the rest of the team!] industry, derring-do, and ingenuity that we are able to convene here at all.
It is a deep shame that Lightcone funding is still precarious. It is a shame that Habryka and his team have been blacklisted from Coefficient Giving funding.
Habryka has been in the forefront on defending free speech norms, often taking principled stances in favour of people expressing unpopular opinions. In a personal capacity, I have worked with Oliver on several occasions and came away with a sense that he was highly competent and morally courageous.
That is all to say, I say this with love, care and a deep appreciation of Habryka & Lightcone’s work, morals and achievements.
Dear Habryka, you have shown great courage and eloquence in hectoring powerful figures and organizations in public, occasionally to the severe financial detriment of you and your organisation. You have been a tireless advocate, in speech and action, that speaking truth to power is a moral duty. So allow me to to follow your example and write this publicly. This is not the way. I hope you reflect and reconsider.
I think Habryka’s tweet there is totally reasonable.
By default, I think it’s totally fine for people to use evidence and reason to make choices about which other people they want to support in various ways. This is the obvious default, and perhaps we don’t need to say anything more about it, but I’ll elaborate on what I see as the best relevant argument for why this would be bad, and explain why I don’t think it applies here:
In some cases, people build infrastructure where they promise not to use the power they get from running the infrastructure in various ways. For example, it would be considered totally unacceptable for LessWrong or Facebook or whatever to post people’s private messages in order to accomplish their objectives. And I think it’s reasonable for users of Twitter to not like it if the algorithm is specifically designed to boost certain political views. As another example, MATS uses an external council to decide which mentors should be supported by MATS; they are explicitly trying to avoid consolidating a certain type of power so that other actors (in this case, maybe mostly funders) are happier to empower them in other ways.
But that’s not what’s happening here. Hypothetically, Lightcone could have claimed that they would provide free space for any event that was approved of by a broad swathe of AI safety people, so that AI safety people were more willing to empower Lightcone. But that didn’t happen at all. Lightcone never said that. Oli is just using the authority that he has as the leader of an organization to take actions in a way that I think is totally consistent with the expectations he’s tried to set with his public communications.
Of course Habryka has the right to run Lightcone as he sees fit. However, when you retaliate like the way he is considering doing with Scott Alexander—it has a real and negative impact on the epistemic health of the community. I think that is very sad and I implore Habryka to reconsider.
Scott Alexander is universally acknowledged to be a most reasonable interlocutors. His positions are very close to that of Habryka—Scott Alexander holds a doomer position that is more extreme than ~90% of the space. He has been unfailingly polite. He represents a huge swathe of the larger AI safety and rationalist space.
LessWrong serves as the public square for the AI safety community; Lightcone has the aspiration of being a lighthouse for the rationalist community, ai safety more broadly [indeed the entire lightcone]. Habryka has been a vocal advocate for strong free speech norms [rightfully so!]. He has defended the right to platform very controversial people and opinions. He has made a big deal of speaking truth to power—yet when he is the powerful party it seems he can see the mote in another but not the beam in his own eye.
I think that Scott’s recent tweets on this topic have actually been sort of unreasonable and impolite.
LessWrong serves as the public square for the AI safety community
Yes, if the proposal was to ban Scott from LessWrong I’d be much more opposed than if it was to (perhaps! this probably won’t even happen!) not host ACX meetups for free.
I think it is has been net positive for people to begin having earnest conversations about their real reasons for things in public rather than filter everything through a particular discourse norms filter that in practice means people don’t share their real reasons.
Scott Alexander is universally acknowledged to be a most reasonable interlocutors. His positions are very close to that of Habryka—Scott Alexander holds a doomer position that is more extreme than ~90% of the space. He has been unfailingly polite. He represents a huge swathe of the larger AI safety and rationalist space.
Hmm, I think that Scott being such a goated writer would make it harder to notice if he is being epistemically sloppy or underhanded in some way (unless of course you happen to be the target). I’m not saying this to accuse Scott of actually failing at this (I haven’t been following or reading this whole thing carefully), but just to point out that “universally acknowledged to be a most reasonable interlocutors” and “unfailingly polite” are not very compelling to me as evidence of virtuous behavior.
Or more specifically, I expect the world in which he is a paragon of virtuous discourse vs the world in which he is not to both leave one with these impressions, due to his skill as a writer.
That’s not to say that it’s impossible to notice such things, but it’s not the sort of information that exists in “universal acknowledgement” or “politeness”, a more personal endorsement would go a lot further.
The question isn’t whether Scott Alexander is right [or virtuous]. I happen to disagree with plenty of things he is saying. That’s all beside the point. The point is that if you have the ideal to support and manage a community dedicated to honest intellectual inquiry then pushing out reasonable, polite, serious thinkers and writers is bad. Especially ones that agree with 90% of your ideology.
What is the endgame here? You think you will be able to convince world governments of a pauze if you kick out the majority of rationalists for not being pure doomer enough?
I think upholding a standard of virtue is a good thing. If Scott is behaving significantly unvirtuously, then it’s reasonable to stop giving him free support (and if not, then it’s probably unvirtuous for Habryka to stop providing support in retaliation). At least for me, the purity of doomerism is not at issue here either way, nor is the extent to which I agree with their object-level claims.
Basically, I think the specific details matter, and that this can’t simply be decided on general reputations.
He has defended the right to platform very controversial people and opinions. He has made a big deal of speaking truth to power—yet when he is the powerful party it seems he can see the mote in another but not the beam in his own eye.
Come on, I am not going to ban Scott Alexander from events here, or LessWrong.
Some of the services Lightcone provides are relatively neutral pieces of infrastructure where access is taken by default as a right, and some of them are highly discretionary where access is a privilege. Whether to actively host ACX meetups at Lighthaven for free is IMO clearly a privilege not a right. We don’t do that for literally anyone else besides the sequences reading groups and a few researchers we are extremely close to.
(Beyond that, I do want to actively set the expectation that I expect to make infrastructure and culture and access decisions in ways that will be driven by pretty complicated inside-view considerations of mine that I do not promise to always make maximally legible or be uncontroversial. I e.g. think it was the right choice to ban Said from LessWrong, and will make similar choices in the future. Please do not later say that you supported me or LessWrong only conditional on me never doing that!)
Of course Habryka has the right to run Lightcone as he sees fit. However, when you retaliate like the way he is considering doing with Scott Alexander—it has a real and negative impact on the epistemic health of the community. I think that is very sad and I implore Habryka to reconsider.
It seems to me that you’re repeating the claim that Oli’s actions are of an adversarial/retaliatory nature, but you’re not responding to the counterpoints (including the one in Oli’s tweet) that they are more akin to withdrawing support because he comes to consider the receiver of said support less support-worthy.
That is true. This is not an argument [though I have tried to elucidate in some of the comments]. This is me expressing my displeasure & encouraging Habryka to reflect and reconsider.
I don’t fully buy that this is okay just because the free event space was a donation. Of course, you’re not obligated to fund people you disagree with. But how do you think people will behave if they learn that disagreeing with community orthodoxy will immediately lead to loss of financial support? That would have an obvious chilling effect.
I think this is worse given that Scott was pushing back on precisely this kind of “purity spiral” dynamic, where certain opinions seem to be socially enforced for groupthink reasons (not necessarily endorsing this claim FWIW) - and then Habryka started talking about pulling resources in response to disagreement here. (Being perhaps a little uncharitable here, but that’s how it can be perceived.)
Of course Habryka is well within his legal rights to withhold financial support here, I empathize with why he would want to, and I don’t think this is so clear cut morally. But it certainly does make me feel uncomfortable.
Ehhhhhhh. If I am a Netflix subscriber, and one of the executives says something I don’t like, and I make a post saying that I’m cancelling my subscription as a result of that that’s entirely within my rights but it’s definitely adversarial.
This may just be a definition thing. I want to use “adversarial” to mean something more than “not maximally cooperative”. I’d describe a position that wants the other party to lose or fail as adversarial. Like, in a zero-sum game, the players are adversaries because one’s win is the other’s loss.
Ceasing to contribute to someone else’s project doesn’t mean you want them to lose, or benefit from their losing; it just means you don’t want to help them win quite as much as you did before.
And publicly objecting to someone’s behavior doesn’t mean you want them to lose; it just means you wish they would change their behavior.
That’s the sense in which I read “adversarial”. Under some different definition, like “not maximally cooperative” or “expressing disapproval”, sure, it could be “adversarial”.
Yeah, I’m not sure English has a word or even phrase which crisply points to expressing displeasure through the performative withdrawal of previous support (e.g. “performative” in the phrase I used is denotationally correct but has the wrong connotations). Perhaps “conspicuous withdrawal of patronage”? Doesn’t carry any misleading connotations but feels pretty clunky.
This is not the way. I hope you reflect and reconsider.
I am somewhat confused that this whole comment is written as if a thing will happen by default, and I should “reconsider”. Like, are you saying I should reconsider my general policy here?
My tweet ends straightforwardly with “my guess is it’s all unlikely to happen and this is all a hypothetical”, so I am a bit unsure what’s going on here. I mean, it seems fine for you to throw your opinion into the ring (and I would be happy about input and arguments) but I don’t think there is anything to “reconsider” because things are still very solidly in the “consider” phase.
I appreciate much in this comment, but from my perspective Habryka addresses this concern directly in the quote. I don’t view this as petty or adversarial action, I view this as the (deeply sad) ending of a relationship & breakdown of trust.
(Also to be clear it has not happened yet and they are still talking more in private.)
I don’t view this as [...] adversarial action, I view this as the (deeply sad) ending of a relationship & breakdown of trust.
What does the word adversarial mean to you? That’s a serious question. If you’re ending a relationship over a breakdown of trust, presumably that’s because you think you and your counterparty’s interests are misaligned, such that you’ll behave adversarially to each other in situations where those interests are in conflict. Right? What am I missing here?
I’m worried that a lot of people might be laboring under a folk misconception that “cooperation” is something Good people do, while “defecting” or being “adversarial” is something Bad people do, when that’s really not what these terms mean. Game theory doesn’t moralize; it’s the mathematical structure of the universe that morality lives inside.
Mm, how am I using it in this context? I think that there are graceful ways to end a working (or other) relationship that are not intended punitively. Like, you could pull out of a business deal at a critical moment, in order to cause the most cost that you can to the counter-party, and I would consider that actively adversarial/punitive. But I think it is standard for good-faith business deals to allow either party to graceful back out, and that’s considered acceptable and sad but something you signed up for and that you both agree don’t count as an additional imposition.
I can’t escape the thought that if you are at the point of kicking out Scott Alexander you should consider if you are contributing to evaporative cooling.
Again- Scott speaks for a vast group of people within AI safety. He is not paid mouthpiece for the labs or CG or any of the powerful actors. He is ideologically very close to y’all—his views are probably more than doomer than 90% of people in AI safety broadly. I know Habryka vehemently denies this but from the outside it does very much seem like the narcissism of small differences.
I think I’ve heard your perspective and you’ve heard mine / Habryka’s, and communicating that is I think most of what’s happening here, I’ll bow out of this thread for now.
The owner of this website seems to be willing to entertain petty and adversarial actions against very reasonable people he disagrees with.
Original: https://x.com/ohabryka/status/2043543756977430593
more context: https://x.com/slatestarcodex/status/2042329870076637242
I am quite dismayed by Habryka’s words and ways and I hope he will reconsider them. LessWrong has been without doubt the greatest project for good to have appeared from the greater EA-sphere and indeed- the world. Having witnessed the birth of LW 2.0 I can say with some embarrassment that it was not at all clear that anything like LessWrong could have existed. It is a testimony to Habryka’s [and Ben Pace and the rest of the team!] industry, derring-do, and ingenuity that we are able to convene here at all.
It is a deep shame that Lightcone funding is still precarious. It is a shame that Habryka and his team have been blacklisted from Coefficient Giving funding.
Habryka has been in the forefront on defending free speech norms, often taking principled stances in favour of people expressing unpopular opinions. In a personal capacity, I have worked with Oliver on several occasions and came away with a sense that he was highly competent and morally courageous.
That is all to say, I say this with love, care and a deep appreciation of Habryka & Lightcone’s work, morals and achievements.
Dear Habryka, you have shown great courage and eloquence in hectoring powerful figures and organizations in public, occasionally to the severe financial detriment of you and your organisation. You have been a tireless advocate, in speech and action, that speaking truth to power is a moral duty. So allow me to to follow your example and write this publicly. This is not the way. I hope you reflect and reconsider.
I think Habryka’s tweet there is totally reasonable.
By default, I think it’s totally fine for people to use evidence and reason to make choices about which other people they want to support in various ways. This is the obvious default, and perhaps we don’t need to say anything more about it, but I’ll elaborate on what I see as the best relevant argument for why this would be bad, and explain why I don’t think it applies here:
In some cases, people build infrastructure where they promise not to use the power they get from running the infrastructure in various ways. For example, it would be considered totally unacceptable for LessWrong or Facebook or whatever to post people’s private messages in order to accomplish their objectives. And I think it’s reasonable for users of Twitter to not like it if the algorithm is specifically designed to boost certain political views. As another example, MATS uses an external council to decide which mentors should be supported by MATS; they are explicitly trying to avoid consolidating a certain type of power so that other actors (in this case, maybe mostly funders) are happier to empower them in other ways.
But that’s not what’s happening here. Hypothetically, Lightcone could have claimed that they would provide free space for any event that was approved of by a broad swathe of AI safety people, so that AI safety people were more willing to empower Lightcone. But that didn’t happen at all. Lightcone never said that. Oli is just using the authority that he has as the leader of an organization to take actions in a way that I think is totally consistent with the expectations he’s tried to set with his public communications.
Of course Habryka has the right to run Lightcone as he sees fit. However, when you retaliate like the way he is considering doing with Scott Alexander—it has a real and negative impact on the epistemic health of the community. I think that is very sad and I implore Habryka to reconsider.
Scott Alexander is universally acknowledged to be a most reasonable interlocutors. His positions are very close to that of Habryka—Scott Alexander holds a doomer position that is more extreme than ~90% of the space. He has been unfailingly polite. He represents a huge swathe of the larger AI safety and rationalist space.
LessWrong serves as the public square for the AI safety community; Lightcone has the aspiration of being a lighthouse for the rationalist community, ai safety more broadly [indeed the entire lightcone]. Habryka has been a vocal advocate for strong free speech norms [rightfully so!]. He has defended the right to platform very controversial people and opinions. He has made a big deal of speaking truth to power—yet when he is the powerful party it seems he can see the mote in another but not the beam in his own eye.
I think that Scott’s recent tweets on this topic have actually been sort of unreasonable and impolite.
Yes, if the proposal was to ban Scott from LessWrong I’d be much more opposed than if it was to (perhaps! this probably won’t even happen!) not host ACX meetups for free.
I think it is has been net positive for people to begin having earnest conversations about their real reasons for things in public rather than filter everything through a particular discourse norms filter that in practice means people don’t share their real reasons.
Hmm, I think that Scott being such a goated writer would make it harder to notice if he is being epistemically sloppy or underhanded in some way (unless of course you happen to be the target). I’m not saying this to accuse Scott of actually failing at this (I haven’t been following or reading this whole thing carefully), but just to point out that “universally acknowledged to be a most reasonable interlocutors” and “unfailingly polite” are not very compelling to me as evidence of virtuous behavior.
Or more specifically, I expect the world in which he is a paragon of virtuous discourse vs the world in which he is not to both leave one with these impressions, due to his skill as a writer.
That’s not to say that it’s impossible to notice such things, but it’s not the sort of information that exists in “universal acknowledgement” or “politeness”, a more personal endorsement would go a lot further.
The question isn’t whether Scott Alexander is right [or virtuous]. I happen to disagree with plenty of things he is saying. That’s all beside the point. The point is that if you have the ideal to support and manage a community dedicated to honest intellectual inquiry then pushing out reasonable, polite, serious thinkers and writers is bad. Especially ones that agree with 90% of your ideology.
What is the endgame here? You think you will be able to convince world governments of a pauze if you kick out the majority of rationalists for not being pure doomer enough?
I think upholding a standard of virtue is a good thing. If Scott is behaving significantly unvirtuously, then it’s reasonable to stop giving him free support (and if not, then it’s probably unvirtuous for Habryka to stop providing support in retaliation). At least for me, the purity of doomerism is not at issue here either way, nor is the extent to which I agree with their object-level claims.
Basically, I think the specific details matter, and that this can’t simply be decided on general reputations.
Come on, I am not going to ban Scott Alexander from events here, or LessWrong.
Some of the services Lightcone provides are relatively neutral pieces of infrastructure where access is taken by default as a right, and some of them are highly discretionary where access is a privilege. Whether to actively host ACX meetups at Lighthaven for free is IMO clearly a privilege not a right. We don’t do that for literally anyone else besides the sequences reading groups and a few researchers we are extremely close to.
(Beyond that, I do want to actively set the expectation that I expect to make infrastructure and culture and access decisions in ways that will be driven by pretty complicated inside-view considerations of mine that I do not promise to always make maximally legible or be uncontroversial. I e.g. think it was the right choice to ban Said from LessWrong, and will make similar choices in the future. Please do not later say that you supported me or LessWrong only conditional on me never doing that!)
It seems to me that you’re repeating the claim that Oli’s actions are of an adversarial/retaliatory nature, but you’re not responding to the counterpoints (including the one in Oli’s tweet) that they are more akin to withdrawing support because he comes to consider the receiver of said support less support-worthy.
That is true. This is not an argument [though I have tried to elucidate in some of the comments]. This is me expressing my displeasure & encouraging Habryka to reflect and reconsider.
(I didn’t quite understand this, though it was the vibe I was getting. This comment clarifies that.)
Not-donating-money is not “adversarial”, it’s the default condition.
I don’t fully buy that this is okay just because the free event space was a donation. Of course, you’re not obligated to fund people you disagree with. But how do you think people will behave if they learn that disagreeing with community orthodoxy will immediately lead to loss of financial support? That would have an obvious chilling effect.
I think this is worse given that Scott was pushing back on precisely this kind of “purity spiral” dynamic, where certain opinions seem to be socially enforced for groupthink reasons (not necessarily endorsing this claim FWIW) - and then Habryka started talking about pulling resources in response to disagreement here. (Being perhaps a little uncharitable here, but that’s how it can be perceived.)
Of course Habryka is well within his legal rights to withhold financial support here, I empathize with why he would want to, and I don’t think this is so clear cut morally. But it certainly does make me feel uncomfortable.
Ehhhhhhh. If I am a Netflix subscriber, and one of the executives says something I don’t like, and I make a post saying that I’m cancelling my subscription as a result of that that’s entirely within my rights but it’s definitely adversarial.
This may just be a definition thing. I want to use “adversarial” to mean something more than “not maximally cooperative”. I’d describe a position that wants the other party to lose or fail as adversarial. Like, in a zero-sum game, the players are adversaries because one’s win is the other’s loss.
Ceasing to contribute to someone else’s project doesn’t mean you want them to lose, or benefit from their losing; it just means you don’t want to help them win quite as much as you did before.
And publicly objecting to someone’s behavior doesn’t mean you want them to lose; it just means you wish they would change their behavior.
That’s the sense in which I read “adversarial”. Under some different definition, like “not maximally cooperative” or “expressing disapproval”, sure, it could be “adversarial”.
Yeah, I’m not sure English has a word or even phrase which crisply points to expressing displeasure through the performative withdrawal of previous support (e.g. “performative” in the phrase I used is denotationally correct but has the wrong connotations). Perhaps “conspicuous withdrawal of patronage”? Doesn’t carry any misleading connotations but feels pretty clunky.
I am somewhat confused that this whole comment is written as if a thing will happen by default, and I should “reconsider”. Like, are you saying I should reconsider my general policy here?
My tweet ends straightforwardly with “my guess is it’s all unlikely to happen and this is all a hypothetical”, so I am a bit unsure what’s going on here. I mean, it seems fine for you to throw your opinion into the ring (and I would be happy about input and arguments) but I don’t think there is anything to “reconsider” because things are still very solidly in the “consider” phase.
I appreciate much in this comment, but from my perspective Habryka addresses this concern directly in the quote. I don’t view this as petty or adversarial action, I view this as the (deeply sad) ending of a relationship & breakdown of trust.
(Also to be clear it has not happened yet and they are still talking more in private.)
What does the word adversarial mean to you? That’s a serious question. If you’re ending a relationship over a breakdown of trust, presumably that’s because you think you and your counterparty’s interests are misaligned, such that you’ll behave adversarially to each other in situations where those interests are in conflict. Right? What am I missing here?
I’m worried that a lot of people might be laboring under a folk misconception that “cooperation” is something Good people do, while “defecting” or being “adversarial” is something Bad people do, when that’s really not what these terms mean. Game theory doesn’t moralize; it’s the mathematical structure of the universe that morality lives inside.
Mm, how am I using it in this context? I think that there are graceful ways to end a working (or other) relationship that are not intended punitively. Like, you could pull out of a business deal at a critical moment, in order to cause the most cost that you can to the counter-party, and I would consider that actively adversarial/punitive. But I think it is standard for good-faith business deals to allow either party to graceful back out, and that’s considered acceptable and sad but something you signed up for and that you both agree don’t count as an additional imposition.
“Why are mommy and daddy fighting?”
I can’t escape the thought that if you are at the point of kicking out Scott Alexander you should consider if you are contributing to evaporative cooling.
Again- Scott speaks for a vast group of people within AI safety. He is not paid mouthpiece for the labs or CG or any of the powerful actors. He is ideologically very close to y’all—his views are probably more than doomer than 90% of people in AI safety broadly. I know Habryka vehemently denies this but from the outside it does very much seem like the narcissism of small differences.
I think I’ve heard your perspective and you’ve heard mine / Habryka’s, and communicating that is I think most of what’s happening here, I’ll bow out of this thread for now.