*Another* Double Crux Framework

post by Raemon · 2018-05-28T23:30:32.891Z · LW · GW · 7 comments

Epistemic Status: Untested hypothesis. Looking to operationalize better.

Followup to:

A problem with resolving deep disagreements is that there's a lot of finnicky moving parts to the dispute. It's easy to bring up 3 examples to illustrate a point, then you get fixated on one of the examples, and then bring up some adjaecent issues to those examples, and then hours (or months) later you've managed to go in circles three times and still not really resolve anything.

I just had an idea, which may or may not work but I'd like to try (and I have something like 3-5 outstanding deep disagreements with 3-4 different people so it seemed like an opportune time to flesh it out), which is to manage the deep disagreement via a google doc, divided into sections:

1. Common beliefs – What do we actually agree on?

2. Empirical Checks / Bets – What things you can go look at in the real world that'd resolve common cruxes?

3. Common cruxes – What do we agree that we disagree on? (that we have operationalized, such that we are confident we understand each other, and can think productively about how to empirically resolve them)

4. Passing Each Other's ITT [LW · GW] – Each person attempts to summarize each other's position as best they can, in succinct bullet point form. (Contains a subsection for each participant)

5. Amorphous exploratory discussion / ranting – Two large meandering sections that attempt to suss out the parts of the disagreement where you aren't actually sure what each other are saying. Still try to keep points to individual bullets.

This can be done in tandem with an in person discussion. But the main idea here is have an explicit goal that bullet points slowly get refactored into clearer versions of themselves, and move up the hierarchy. Amorphous rants should turn into ITT-passing arguments should turn into clearly identified common cruxes should turn into empiricism should turn into shared beliefs. (And, hopefully, a lot of disagreements dissolve under scrutiny such that empiricism isn't even necessary)

This would give you a clear sense of whether you're accomplishing anything – if the bottom sections keep getting bigger and don't eventually move to the upper sections, you're probably talking in circles, or making some kind of error mode. You might or might not get to the end (where all you have is common beliefs), because empiricism can be expensive, but hopefully at least you transmute things up into the common crux section.

7 comments

Comments sorted by top scores.

comment by zulupineapple · 2018-05-29T10:25:33.372Z · LW(p) · GW(p)

It looks very appealing, but, as was already pointed out, it's not a lightweight approach.

Maybe it could be though? One improvement would be to be able to stick with LW comment format, or any text message format. I think that could still work. We could agree on a set of tags/prefixes, instead of static sections. E.g. [I think we both believe] that ..., [I would bet] that ..., [Let me try to pass your ITT] ..., etc. The amorphous discussion probably does not need to be tagged. And the point of having tags, is that you can then ctrl-F the whole discussion thread to find them, and you can talk about them as objects, or point out that some tags are missing (e.g. that your opponent has not suggested any bets).

Of course, many discussions could be hard to tag, and maybe we'd discourage discussions on those topics, if we pushed such a norm, but if this does actually improve the resolution of disagreements even a little, it might still be worth it.

Replies from: Raemon
↑ comment by Raemon · 2018-05-30T00:35:56.609Z · LW(p) · GW(p)

Thanks, I appreciate the problem solving approach here.

I definitely think clearer norms encouraging the various sorts of thing you suggest tagging here is good. Literally tagging them might also help for the reasons you've noted. I suspect that getting the bulk of the value I was pointing at requires some kind of additional infrastructure.

Most of the value I saw of the framework here was as a working-memory aid, where I think it matters that you can quickly scan the thing at a glance. Ctrl-Fing the sounds like you'd get some of the value, but I'm suspect the overhead/benefit ratio would end up being similar to the OP. (i.e. less cost, but also less benefit)

There's been periodic attempts to create formal Double Crux frameworks, with I think usually suffer from being a) unwieldy, b) not really suited for how people actually have conversations. This framework shares that issue, but something that made me a bit more optimistic than usual about it is that I've had a lot of good experiences using google docs as a way to hash out ideas, with the ability to blend between formal bullet points, freeforming paragraphs, and back-and-forth conversation in the comments as needed.

AsI said to Chris_Leong, I'd still only recommend this as a supplement for when you've already tried once or twice to just talk through the thing seriously.

Replies from: zulupineapple
↑ comment by zulupineapple · 2018-05-30T13:34:37.928Z · LW(p) · GW(p)
There's been periodic attempts to create formal Double Crux frameworks

Do you have any links about those, or specifically about how they fail?

To be honest, I think it's likely that the whole idea of formalizing that sort of thing is naive, and only appeals to a certain kind of person (such as myself), due to various biases. Still, I have some hope that it could work, at least for such people.

This framework shares that issue, but something that made me a bit more optimistic than usual about it is that I've had a lot of good experiences using google docs as a way to hash out ideas, with the ability to blend between formal bullet points, freeforming paragraphs, and back-and-forth conversation in the comments as needed.

Do elaborate. Did "hashing out ideas" involve having many disagreements? Did the ideas relate to anything controversial, or were they more technical? Where the people you collaborated with "rationalists"? Did you feel much resistance from them, to doing anything even remotely formal?

Replies from: Raemon
↑ comment by Raemon · 2018-05-31T00:06:40.055Z · LW(p) · GW(p)

I looked for the DoubleCrux website but couldn't find it (I think Lifelonglearner made it). [fake edit: tried very slightly harder and then found it: http://double-crux.appspot.com/]

I think it's likely that the whole idea of formalizing that sort of thing is naive, and only appeals to a certain kind of person (such as myself), due to various biases

I think most attempts have something of this quality.

My own motivation came specifically because of some debates that went for several months and didn't seem to have resolved anything.

Did "hashing out ideas" involve having many disagreements? Did the ideas relate to anything controversial, or were they more technical? Where the people you collaborated with "rationalists"? Did you feel much resistance from them, to doing anything even remotely formal?

1. yes – I regularly hash out disagreements on google docs. I haven't had to do deep worldview disagreements, but standard disagreements within a shared frame. Some of the ideas were "controversial", but not frame-breakingly controversial among the people discussing them.

2. yes, basically entirely rationalists that I trust reasonably

3. Not sure I parse the third question – I didn't feel much resistance one way or another. (The structure here was "write an initial braindump on google docs, then invite people hash out disagreements in the comments).

(I'd only suggest the DoubleCrux framework in the OP for people who trust or at least meta-trust each other)

Replies from: zulupineapple
↑ comment by zulupineapple · 2018-05-31T08:32:05.675Z · LW(p) · GW(p)
The structure here was "write an initial braindump on google docs, then invite people hash out disagreements in the comments

Is it possible that you did 90% of the work on those docs, at least of the kind that collects and cleans up existing arguments? This is sort of what I meant by "resistance". E.g. if I wanted to have a formalized debated with my hypothetical grandma, she'd be confused about why I would need that, or why we can't just talk like normal people, but this doesn't mean that she wouldn't play along, or that I wouldn't find the results of the debate useful. I wonder what fraction of people, even rationalists, would feel similarly.

http://double-crux.appspot.com/

Well, that has fewer moving parts and fewer distinct kinds of text than I would appreciate. But I suspect that the greatest problem with this sort of thing would be a lack of persistent usage. That is, if a few people actually dedicated effort into having disagreements with a similar tool, even this simple, they might draw some benefit from it. But since such tools aren't the least effort option for anybody, they end up unused. I guess google docs are pretty good in this sense, in that everyone has access to them, the docs are persistent and live in a familiar place (assuming the person uses google docs for other purposes), and maybe you can even be notified somehow, that "person X modified doc Y".

comment by Chris_Leong · 2018-05-29T05:36:33.261Z · LW(p) · GW(p)

That's a very interesting idea. It seems that these would have to be pretty important disagreements in order for you to want to invest this much time in attempting to resolve them. But please update us after you've had an opportunity to actually try this framework!

Replies from: Raemon
↑ comment by Raemon · 2018-05-29T06:07:58.396Z · LW(p) · GW(p)

I ended up not using it on the first of the deep disagreements I had floating around, because it felt like it might constrain the conversation a bit. My new, small update is to officially note that I'd definitely recommend first trying the usual thing of "talk about it for a few hours and see if you can come to agreement or something close to it", and yeah, only bust out something like this if you've tried that at least once or twice and it didn't seem sufficient.