Tell people as early as possible it’s not going to work out
Context: Post #4 in my sequence of private Lightcone Infrastructure memos edited for public consumption
This principle is more about how I want people at Lightcone to relate to community governance than it is about our internal team culture.
As part of our jobs at Lightcone we often are in charge of determining access to some resource, or membership in some group (ranging from LessWrong to the AI Alignment Forum to the Lightcone Offices). Through that, I have learned that one of the most important things to do when building things like this is to try to tell people as early as possible if you think they are not a good fit for the community; for both trust within the group, and for the sake of the integrity and success of the group itself.
E.g. when you spot a LessWrong commenter that seems clearly not on track to ever be a good contributor long-term, or someone in the Lightcone Slack clearly seeming like not a good fit, you should aim to off-ramp them as soon as possible, and generally put marginal resources into finding out whether someone is a good long-term fit early, before they invest substantially in the group.
There are two related reasons that push towards this principle:
First, and this is the less important reason, it usually benefits the person you are asking to leave. They likely have a substantial opportunity cost, and little is achieved by stringing them along in a situation you know is unsustainable. People form relationships within communities and groups like ours, and if you know you will tear them apart, better to do so early.
Second, and this is unfortunately the more important reason, is that it is much easier to destroy than to create, and most intense enemies seem to be former members who invested too much before they eventually were asked to leave or cut off some other way. As far as I can tell, it requires a certain kind of intense experience to cause someone to want to invest many hundreds of hours into destroying something, and “feeling betrayed after having made some place their home” is among the top one of those.
In at least the rationality community’s history, most of the people who I think have most actively tried to destroy it, have been former members who invested quite a lot:
David Gerard
Eugine Nier
Émile Torres
Ziz (and most of the Zizians)
Two cases that are a bit less clear, but still show some structural similarities: Peter Thiel, Sam Altman.
Case of someone who does sure seem to hate AI safety people and EAs and probably also rationalists, but who as far as I know never meaningfully was part of it: David Sacks
So, when you are in charge of some kind of group boundary, do the following:
Inasmuch as possible, set up the group to evaluate early whether any long-term members are a good fit
If you know someone isn’t going to work out, try to pay the cost to kick them out early instead of late
Try to prevent “slums” forming where people who don’t meet your group’s standard congregate (this generally gets more likely the later you kick out people)
Related reading: The Tale of Alice Almost: Strategies for Dealing With Pretty Good People
I suppose that this is very dependent on how you know, and how confident you are. I have seen cases where I agree, but I’ve also seen the opposite problem of being too selective breeding homogeneity, resentment, and cults.
The times I have seen communities dissolve were not due to people that weren’t a good fit, but instead it’s been the people that fit well (usually in leadership), but had a big falling out with other members (usually leadership).
From personal experience, I’d be weary of defending the community from drama. It’s a dangerous motivation: that’s one way to enable abusive behavior. Saving people by hurting them is a dangerous motivation too, as it’s easy to justify one’s own bad behavior—yeah, I’ve done that too.
Again though, this is all highly context dependent. I am not familiar with most of your examples, so I can’t talk to specifics. I have also regretted not stepping in sooner.
Community leadership is hard, y’all.
In any case, thanks for the perspective, and the reminder of that line.
Do you have a target precision / accuracy for early-notifying?
Are you concerned about capriciousness? It’s a negative effect on a community if one mod bans/fires someone for illegible reasons. In the case of hiring/firing it has compliance risk.
Is there actually a problem with people knowing something isn’t going to work out, then sitting on it for a while anyway? I’m really guessing in these situations you’d find they think there’s big complications, or possibly a hidden process reason, with acting too early.
By the way I think I replied to your pro-DIY article. I think a theme between the two is you didn’t identify that these things are tradeoffs. At best, you’re insightful that people go too much in the other direction, but you didn’t articulate what that other direction is, or why they might sometimes do it. Ideally you have something more like a rubric or pros/cons lists for when to go one way or the other.
I will say that bad people who are around too long sometimes become destroyers is a novel point to me. I would have simply modeled them as linear lost time, joy or effort. I don’t know if “revenge tour” bad people are easily screenable early and don’t know these 4 cases well enough.
Also to your point—I looked at the case of one of the “banned” users. You can tell the mod who banned them wanted moral points for being cautious and democratic but not for being fast or effective. They didn’t seem to ascribe a cost to being too cautious.
Also I wouldn’t condense and repeat our list of enemies. It’s not respectful to them, gives them publicity, risks reopening the conflict. It’s supposed to be in the past. I looked into one of them and he was banned on bad terms. Torres—to my knowledge—you can mention because it’s on civil terms and it’s more like a professional disagreement, but I don’t have full context here. Dunno about the other 2.
I think this would be actively bad for a set of internal company principles! Facebook’s central motto was “Move fast and break things” not “Move fast and break things in this situation, but not in this other situation”. The latter doesn’t really work as a principle!
The conditional for all of these principles is “what I think is the right choice for someone working at Lightcone”. Much of the force of these principles comes from conditioning on our specific context. The force of a company culture principle comes from all the behaviors that are appropriate in other contexts that it rules out as not being appropriate in this context.