The Charge of the Hobby Horse

[-]Wei Dai1d250

It appears from this post that the ban was itself based on a misunderstanding of my final comment. Nowhere in my comment did I say anything resembling "Anyway, let's talk about how Y is not true." with Y being "People should have been deferring to Yudkowsky as much as they did."

What I actually did was acknowledge my misunderstanding and then propose a new, related topic I thought might be interesting: the actual root causes of the deference. This was an invitation to a different conversation, which Tsvi was free to ignore.

There is no plausible interpretation of my comment as a refusal to drop the original point. The idea that I was stuck on a hobby horse that could only be stopped by a ban is directly contradicted by the text of the comment itself:

Ok, it looks like part of my motivation for going down this line of thought was based on a misunderstanding. But to be fair, in this post after you asked "What should we have done instead?" with regard to deferring to Eliezer, you didn't clearly say "we should have not deferred or deferred less", but instead wrote "We don't have to stop deferring, to avoid this correlated failure. We just have to say that we're deferring." Given that this is a case where many people could have and should have not deferred, this just seems like a bad example to illustrate "given that to some extent at the end of the day we do have to defer on many things, what can we do to alleviate some of those problems?", leading to the kind of confusion I had.

Also, another part of my motivation is still valid and I think it would be interesting to try to answer why didn't you (and others) just not defer? Not in a rhetorical sense, but what actually caused this? Was it age as you hinted earlier? Was it just human nature to want to defer to someone? Was it that you were being paid by an organization that Eliezer founded and had very strong influence over? Etc.? And also why didn't you (and others) notice Eliezer's strategic mistakes, if that has a different or additional answer?

I think there are other significant misrepresentations in his "gloss" of the thread, that I won't go into. This episode has given me quite a large aversion around engaging with Tsvi, which will inform my future participation on LW.

[-]TsviBT1d3-7

It appears from this post that the ban was itself based on a misunderstanding of my final comment.

No. The original ban was based on the pattern I described. The pattern is that you really wanted to talk about Y, but instead of just saying so, you tried to fabricate a disagreement with me (initially about X) and did not listen to me saying I did not think Y.

Nowhere in my comment did I say anything resembling "Anyway, let's talk about how Y is not true." with Y being "People should have been deferring to Yudkowsky as much as they did."

I mean, you switched the topic from X to the general topic of people deferring too much to Yudkowsky (Y). Is your point here that you didn't literally switch to arguing in favor of the proposition Y, but rather switched to asking what led to Y being the case? This is a nitpick--a distinction without a difference in the context where I'm describing the X-Y pattern. Do you see this at all? Like, the pattern I'm describing is that you really want to talk about Y, but instead of just talking about it you're going on about X because that's what you think you can pick a fight with me about, and ignoring when I'm saying I don't disagree with Y while still moving the discussion to the topic of Y.

[-]Zack_M_Davis1d2713

did not listen to me saying I did not think Y.

But it really seems like you do have a significant disagreement with Dai about the extent to which deference to Yudkowsky was justified.

I understand and acknowledge that you think deference has large costs, as you've previously written about. I also understand and acknowledge that you think defering to Yudkowsky on existential risk strategy in particular was costly, as you explicitly wrote in the post ("one of those founder effects was to overinvest in technical research and underinvest in 'social victory' [...] Whose fault was that?").

At the same time, however, in your discussion in the post of how people could have done better in that particular case, you emphasize being transparent about deference in order to reduce its distortionary effects ("We don't have to stop deferring, to avoid this correlated failure"), in contrast to how Dai argues in the comment section that not-deferring was a live option ("These seemed like obvious mistakes even at the time"). You even seem to ridicule Dai for this ("And then you're like 'Ha. Why not just not defer?'"). This seems like a real and substantive disagreement, not a hallucination on Dai's part. It can't simultaneously be the case that Dai is wrong to implicitly ask "Why not just not defer?", and also wrong to suggest that you disagree with him about when it's reasonable to defer.

[-]TsviBT22h-1-2

It can't simultaneously be the case that Dai is wrong to implicitly ask "Why not just not defer?",

Is that what you think I said?

[-]Jiro1d64

Is your point here that you didn’t literally switch to arguing in favor of the proposition Y, but rather switched to asking what led to Y being the case? This is a nitpick—a distinction without a difference

Here you seem to be saying that someone might not be literally arguing for something, but he might in effect be doing so anyway.

Yet your original post seems to reject that concept. Here you claim that Zack is wrong because he did not take someone's words literally, and instead did interpret those words to be in effect saying something:

“But if I take your specific word choice and imagine a whole epistemological stance that produced that word choice, I disagree with that epistemological stance because of such-and-such.”

[-]TsviBT10h1-2

I'd probably need more proof-of-work of understanding to want to continue engaging

[-]Zack_M_Davis1d2312

I'm going to stand by the "framing as a correction" in my initial comment on "There's no such thing as a tree (phylogenetically)". (The "sorry" in my final comment was intended as a sympathy-for-not-loving-how-the-thread-ended-up-playing-out sorry—it was just not a great thread for several reasons—not an admission-of-wrongdoing sorry.)

What I took issue with in the post was the conjunction of a recommendation to "Acknowledge that all of our categories are weird and a little arbitrary" and an endorsement of "The Categories Were Made For Man, Not Man For The Categories". I claim that this was substantively misleading readers about the cognitive function of categorization. I think that was a real flaw in the post that I had a legitimate interest in pointing out, and I'd do it again.

It's true that my comment was somewhat tangential to the main thesis of the post. Eukaryote was primarily trying to share some cool Tree Facts, not push a philosophy-of-language thesis. I don't think that bears on the propriety of my comment. If in the course of trying to share Tree Facts, you end up accidentally saying something substantively misleading about the philosophy of language, you should expect a comment from your local philosophy of language specialist.

(In the same way, if in the course of trying to push my philosophy of language thesis, I accidentally end up saying something misleading about trees, I expect a comment from my local tree specialist. I promise not to take it personally, because I know it's not about me and my intent: it's about having a maximally accurate shared map of trees. It's good for specialists to comment on flaws in a post, even if they're tangential to the post's main thesis, because then people who read the comments can be better informed about that tangential point. It shouldn't detract from other comment threads discussing the main thesis of the post; we're not going to run out of paper.)

It's true that after I explained how I think the cognitive function of categorization bears on the question of trees, Eukaryote wrote that "it doesn't sound like we disagree" and that I was "over-extrapolating what [she] meant by arbitrary". I don't think that bears on the propriety of my comment. When I leave a comment on a post, I'm commenting on the text of the post, not the author's private belief-state (which I obviously don't have access to). If it turns out the author actually agrees with my comment, that doesn't necessarily mean it was a bad comment unless it was already clear from the post that the author would agree.

[-]TsviBT22h12-2

It's true that my comment was somewhat tangential to the main thesis of the post. Eukaryote was primarily trying to share some cool Tree Facts, not push a philosophy-of-language thesis. I don't think that bears on the propriety of my comment.

I agree, and said as much in the post (in general terms) in the conclusion.

I don't think that bears on the propriety of my comment. When I leave a comment on a post, I'm commenting on the text of the post, not the author's private belief-state (which I obviously don't have access to).

This is pretty absurd, but I'm sure you've litigated this point many times, so I assume there's little reason for me to try to get you to see something new here. So it's at least hinted somewhere, there's a relevant difference between responding to [the text where someone makes their case repeatedly in detail] vs. [the text where someone makes a very tangential point in one phrase or sentence and doesn't elaborate on their position]. It's perhaps not a coincidence that you pick up on tangential points. This would be predicted by "Zack is looking for words that he can then respond to by talking about his hobby horse". Which again would be fine! I think you yourself have done this in perfectly fine ways! But I think for example you should be clear about when you're doing this, including about how you're not really trying to dialogue with the author's intent; or if you are trying to do that, then you can just take a sentence to check what they think. It's good practice anyway to state the position you're critiquing. So then you can just ask the author "is this roughly what you think?". Then they could say yes or no or a more nuanced answer or "IDK but I don't feel like talking about that".

Even if you are (or claim) to be only responding to text, just as though it were LLM-generated text that someone happened to post (and got a lot of attention that you perhaps wanted to piggyback off of?), you can maybe understand that usually other people are making guesses at the author's belief-state (which is not private, since they have written from it), and then trying to dialogue with that belief-state e.g. in the comments on that post, so it makes sense that authors might presume that commenters are doing that.

also that's how discourse ought to work oki byeeeee

[-]Benquo5h*10

I don't see what good option you're offering Zack, given the discursive environment.

If everyone is unreflectively endorsing harmful nonsense A and referencing a canonical case for A, it makes sense to FIRST argue against the canonical case. But if people keep behaving as though they hadn't read the argument and endorsing A anyway, the options are:

1 Assume good faith, treat this as evidence of ignorance, and try to point them to the correction.

2 Infer bad faith and try to recruit others to invalidate this vice-signaling.

3 Give up and go away.

Seems like Zack's doing 1, and I've done a mixture. I understand that 3 is the rational option in most contexts these days, but this is the RATIONALITY forum, what exactly is Zack supposed to do here? What's the point of any of this if Zack's behavior is unwelcome?

While there really are hobbyhorses in the sense you describe, they are mild inconveniences (trivial in a written medium) like a bore talking about train schedules on the flimsiest pretext. The use you're making of the idea here just seems like a projection. There's some shared sense of entitlement to speak without being accountable to certain sorts of criticisms, and the perceived injury of accountability is being projected onto those trying to hold members of this class accountable.

[-]TsviBT3h20

The use you're making of the idea here just seems like a projection. There's some shared sense of entitlement to speak without being accountable to certain sorts of criticisms, and the perceived injury of accountability is being projected onto those trying to hold members of this class accountable.

Can you clarify about this "entitlement to speak without being accountable" that I supposedly have? Are you tracking that I've repeatedly said there's nothing wrong per se with making nitpicks, tangential comments, criticisms, etc.?

[-]Benquo1h50

You banned Wei for articulating what to all appearances was a good-faith objection, and wrote a blog post advertising this as though you expected people to side with you.

You reported the impression that you had the subjective sense it ought to have been easy to find an example of Zack behaving badly, but had some difficulty finding an example you found satisfactory. My impression is that this is a pretty common response to Zack's criticism: there's no specific complaint on Gricean or similar grounds (it's not actually irrelevant, untrue, or unimportant), but there's a sense that one ought to have standing to nonspecifically complain about him because one expects others to share a sense that his criticisms are unwelcome, and to side with the complainer.

It seems like because Scott's politically central in the local social cluster, people feel entitled to approvingly cite his blog post on categories no matter how clearly someone politically marginal explains the problems with it, and for this to be considered a free, default, noncontentious action, like referring to the clear daytime sky as blue, or 2+2=4. But taken literally this behavior is making an important false claim, so objecting to it is always justified on Gricean grounds.

For people who feel entitled to accountability from other speakers, and obliged to account for their own claims, the obvious remedy to these annoyances is for people to stop approvingly citing bad arguments. The sense that instead Zack ought to stop complaining seem like it reflects a (presumptively shared) sense of entitlement not to be bothered when you're being normal, regardless of the literal implications of what you say.

This seems inconsistent with your explicit statement that criticisms and even nitpicks are "okay." I was trying to explain the behavior I observed, not the different preferences described.

[-]TsviBT1h20

You banned Wei for articulating what to all appearances was a good-faith objection

No, I banned him for the pattern I described in this post, which is fabricating a disagreement and ignoring clarification about that false disagreement in order to talk about his thing.

You reported the impression that you had the subjective sense it ought to have been easy to find an example of Zack behaving badly, but had some difficulty finding an example you found satisfactory. My impression is that this is a pretty common response to Zack's criticism: there's no specific complaint on Gricean or similar grounds (it's not actually irrelevant, untrue, or unimportant), but there's a sense that one ought to have standing to nonspecifically complain about him because one expects others to share a sense that his criticisms are unwelcome, and to side with the complainer.

...But I did find an example fairly easily, and described it, it just wasn't the first couple top-voted comments.

[-]jimmy17h2211

While I understand the frustration, I'd rather have more hobby horse riders here. If I ever say something to inspire the charge of a hobby horse, I want that correction.

Because I might get lazy. Or imprecise. The "correction" might be something I immediately recognize as "obviously true", and want to say "Yeah yeah, that's what I meant". But it might not be what I said, and I may have been underweighting the importance of that little "nitpick" when I was writing. After all, that why there's the charging of the hobby horse; the other person doesn't think it's some unimportant nitpick. And neither do the LW voters, in the cases you highlight.

Maybe it's not.

If we try to discourage people from correcting real errors or misleading representations in the text, simply because the person pointing it out is unusually perceptive in this area, or is unusually aware of the importance of this kind of mistake, then we are in effect saying that we don't want to hear from people who are uniquely suited to correcting specific errors. "Sorry, Eliezer, you've been riding this AI hobby horse too much. We agree that making an unfriendly superintelligence would be bad, which is why we're going to make it friendly. Can't we move on and build it now?".

That doesn't cut it when the issue actually is important, and often the awareness of these things falls on few people. "What is a woman?" exploded into such a huge issue that I'm glad we have our resident "hobby horse rider" here, with skin in the game, motivated to do very careful thinking and call out what he sees to be errors on our part. If he's wrong he's wrong, which is a different criticism. If he's right though, I'd rather amend or clarify my writing to the satisfaction of the person who makes getting this particular thing right their thing. It might save me from mistakes I don't properly appreciate.

The qualifier "to the satisfaction of the other person" is important here. I know you think you've gotten things close enough. Likely so do the other authors in your examples. I also know that the hobby horse riding commenters disagree, and so does the audience -- at least in these cases. And that if you can't pass their ITT you can't know if you're missing something that validates their perspective and invalidates yours. And that if you can, they won't continue to think you don't get it, and therefore won't have reason to post those "unnecessary" comments.

[-]TsviBT10h-10

(I'm unsure if this is addressed at me, but if so, I'd probably need more proof-of-work of understanding to want to continue engaging.)

[-]Thane Ruthenis1d1114

So what is this pattern? I'd call it The Charge of Hobby Horse. It's where you ride your hobby horse into battle in the comments, crashing through obstacles such as "the author did not even disagree with me, so there's nothing to actually have a battle about".

Yeah, I'd noticed that impulse in myself before. I'm consciously on the lookout for it, but it's definitely disappointing to run into something that seems like an opportunity to have an argument about your pet topic, only to realize that that opportunity is a mirage.

[-]TsviBT1d10

Tagging @Zack_M_Davis and @Wei Dai

[-]Wei Dai1d*53

Can you please remove the example involving me, or anonymize it and make it a hypothetical example? I think it's a significant misrepresentation of my words (that makes me appear more unreasonable than I was), but don't have the time/energy/interest to debate you to try to get it corrected. Edit: Since you're refusing this request, I wrote one comment to (partially) give my perspective, but will not be engaging further.

[-]TsviBT1d52

I don't think I should, I think it's better to talk about it. I added a link to your comment before my gloss.

[-]Ben Pace1d*120

There is a persistent miscommunication between you two on this topic. Without attempting to assign fault, I think it's a typical failure mode in this situation to "Keep talking because it seems clear to me, surely at some point they'll get it and apologize". I recommend leaving perhaps a final comment then cutting your losses and moving on, rather than dragging on with a long, unpleasant thread of accusations of (relatively mild) bad behavior and frustratingly never getting on the same page about it.

(Alternatively, I think the move of adding a neutral third-party to a 1-1 convo who both people respect, often makes things way better. If either of you want to propose people and open up DMs, that seems to me more likely to actually resolve anything.)

[-]Raemon21h20

There is a persistent miscommunication between you two on this topic.

For my reference, what's an example of an earlier instance of this miscommunication? Or did you just mean "across the past day-or-two?"

[-]Ben Pace20h40

The initial thread had a lot of miscommunication, then Wei Dai’s shortform seemed to me at least like both sides continued to mostly get negative value (though not marginal miscommunication), and now an IMO good attempt via blogpost to communicate further has still left one party believing they’re totally misrepresented.

[-]Raemon20h20

Thanks, I wasn't sure if there was more history I was missing. Although I had missed the shortform.

[-]TsviBT22h20

Ok. You're probably right. Seems like a bad result though. But I don't necessarily see a good way to get a better result.

[-]Ben Pace20h44

Yeah. I’m saying the interaction has been net negative, and we shouldn’t bet on it not continuing to be :(

[-]Ben Pace1d-3-5

To be clear, I think writing a post with multiple examples capturing why you banned someone seems very pro-social, much better than banning with only a brief explanation.

[-]Wei Dai19h01

Can you clarify whether you or mods as a whole endorse this kind of "shoot first, ask questions later" approach to author moderation? It seems like you're implicitly doing that, by saying that it's "very pro-social"? (It's possible that you only mean this relative to "banning with only a brief explanation", not in an absolute sense, hence the request for clarification.) I think a much better approach would be to explain what one sees as the bad behavior, give a chance for the commenter to change their behavior or defend themselves (maybe the perception of bad behavior itself was wrong), perhaps do third party mediation if the stakes are high enough, and then only ban if none of this worked.

(Disclaimer: This assumes trusting oneself to make this kind of judgment at all, which I don't. I continue to think allowing unilateral author bans is a big mistake, with this episode as yet another illustration. The above was written under the assumption that mods will not change their minds about this.)

Banning first and then trying to discuss poisons the well and makes subsequent conflict resolution much harder. It probably has different effects in different people, but in my case I simply have little to no motivation for talking with Tsvi at this point. Furthermore, I think it makes the whole community worse off, not just Tsvi's own spaces.

[-]Ben Pace17h106

I think it is sad to move straight to a ban. I don't believe that one always needs to put in a lot of effort before being able to accurately come to the conclusion that a commenter's bad behavior is not going to get better, and you don't owe every commenter (say) a dozen hours of advice and mediation, but I think that for long-time users who have made lots of good contributions, a second chance is a good idea, along with giving a warning with a comment pointer to what they thought was bad.

[-]Raemon18h2-3

Since we've already spent quite awhile discussing this, I'd kinda like to ask you to do the work of summarizing your understanding of our current position before re-explaining it to you.

I'm feeling a bit trapped in a "I would like to resolve this more with Wei Dai in particular, but, I don't want to fall into the generic trap of restating our positions over and over in a way that will predictably not lead anyone to change their mind." So I think I'm interested in discussing it more to the extent that we have some plan for building on the previous discussion rather than rehashing.

[-]Wei Dai18h50

My understanding of your position on what? Is it:

Whether LW should allow unilateral author moderation at all? I've already given up on trying to convince the LW team about this. Are you saying that you want to reopen this issue? Or,
Whether you endorse the specific kind of moderation that Tsvi did, namely to ban someone without warning, and then try to discuss it afterwards? I don't think I've seen the mods talk about this before, hence I have no understanding of your position and am asking about it for the first time?

[-]Raemon18h20

I guess what I meant was "I think my beliefs about #2 are fairly derivable from what I or Oli or Ben said in the past, and I can't remember whether I, Oli or Ben already answered this specific question, and didn't feel obligated to do all the work of checking myself."

But, I don't know if that was exactly fair either, I went ahead and answered the question for now.

[-]Raemon18h-3-3

I guess a tl;dr is I don't think Tsvi's approach here was perfect, and sometimes ban-first is bad. (it depends. all else equal it's better for people to put more work into moderating well. But, things are usually not equal and moderating is extremely expensive).

But, the part where he unbanned you a day later, and wrote up a post that included Tsvi himself as an example of a bad pattern he'd like to address, makes me feel like this particular case is overall reasonable. If he hadn't done that, I'd probably be talking privately with Tsvi about it and trying to find something better.

but in my case I simply have little to no motivation for talking with Tsvi at this point

Note that, in the original case, Tsvi had little-to-no-motivation for talking to you (presumably, since he banned you). I don't think you exactly mean this, but this comes across to me as something like "when I do something that results in an author no longer wanting to talk to me, he should suck it up and keep talking to me. But, when they do something that leads me to no longer wanting to talk to them, that's on them."

Presumably you see the cases as being importantly different. That might be, but, I'm not automatically granting that assumption.

[-]Wei Dai14h2-5

A difference is that Tsvi is still plenty motivated to talk on a meta level (about why he banned me), as evidenced by this post. So he could have easily said "I no longer want to talk about the object level. I think you're doing a bad thing, [explanation ...], please change your behavior if you agree, or let me know why you don't (on the meta level)." Or "I'm writing up an explanation of what you're doing wrong in this thread. Let's pause this discussion until I finish it."

Or if he actually doesn't want to talk at all, he could have said "I'm getting really annoyed so I'm disengaging." or "I think you're doing a bad thing here, here's a short explanation but I don't want to discuss it further. Please stop it or I'll ban you."

Note that I'm not endorsing banning or threat of banning in an absolute sense, just suggesting that all of these are more "pro-social" than banning someone out of the blue with no warning. None of these involve asking him to "suck it up and keep talking to me" or otherwise impose a large cost on him.

LESSWRONG
LW

LESSWRONG
LW

56

The Charge of the Hobby Horse

56

56

Case 1: You only get six words

Case 2: Trees may be cool but how should concepts work in general??

Case 3: The Bannination

The Pattern

Conclusion