The LessWrong team is shipping a new experimental feature today: dialogue matching!

I've been leading work on this (together with Ben Pace, kave, Ricki Heicklen, habryka and RobertM), so wanted to take some time to introduce what we built and share some thoughts on why I wanted to build it.

New feature! 🎉

There's now a dialogue matchmaking page at lesswrong.com/dialogueMatching

Here's how it works:

You can check a user you'd potentially be interested in having a dialogue with, if they were too
They can't see your checks unless you match

It also shows you some interesting data: your top upvoted users over the last 18 months, how much you agreed/disagreed with them, what topics they most frequently commented on, and what posts of theirs you most recently read.

Next, if you find a match, this happens:

You get a tiny form asking for topic ideas and format preferences, and then we create a dialogue that summarises your responses and suggests next steps based on them.

Currently, we're mostly sourcing auto-suggested topics from Ben's neat poll where people voted on interesting disagreement they'd want to see debated, and also stated their own views. I'm pretty excited to further explore this and other ways for auto-suggesting good topics. My hypothesis is that we're in a bit of a dialogue overhang: there are important conversations out there to be had, but that aren't happening. We just need to find them.

This feature is an experiment in making it easier to do many of the hard steps in having a dialogue: finding a partner, finding a topic, and coordinating on format.

To try the Dialogue Matching feature, feel free to head on over to lesswrong.com/dialogueMatching !

Me and the team are super keen to hear any and all feedback. Feel free to share in comments below or using the intercom button in the bottom right corner :)

Why build this?

A retreat organiser I worked with long ago told me: "the most valuable part of an event usually aren't the big talks, but the small group or 1-1 conversations you end up having in the hallways between talks."

I think this points at something important. When Lightcone runs events, we usually optimize the small group experience pretty hard. In fact, when building and renovating our campus Lighthaven, we designed it to have lots of little nooks and spaces in order to facilitate exactly this kind of interaction.

With dialogues, I feel like we're trying to enable an interaction on LessWrong that's also more like a 1-1, and less like a broadcasting talk to an audience.

But we're doing so with two important additions:

Readable artefacts. Usually the results of a 1-1 are locked in with the people involved. Sometimes that's good. But other times, Dialogues enable a format where good stuff that came out of it can be shared with others.
Matchmaking at scale. Being a good event organiser involves a lot of effort to figure out who might have valuable conversations, and then connecting them. This can often be super valuable (thought experiment: imagine introducing Von Neumann and Morgenstern), but takes a lot of personalised fingertip feel and dinner host mojo. Using dialogue matchmaking, I'm curious about a quick experiment to try to doing this at scale, in an automated way.

Overall, I think there's a whole class of valuable content here that you can't even get out at all outside of a dialogue format. The things you say in a talk are different from the things you'd share if you were being interviewed on a podcast, or having a conversation with a friend. Suppose you had been mulling over a confusion about AI. Your thoughts are nowhere near the point where you could package them into a legible, ordered talk and then go present them. And ain't nobody got time for that prep work anyway!

So, what do you do? I think a Dialogue with a friend or colleague might be a neat way to get these kinds of thoughts out there.

Using LessWrong's treasure trove of data

Before I joined the team, the LessWrong crew kept busy shipping lots of stuff. So now when readers and writers hang out around here, there's lots of data we create about what we find interesting. There are:

...tags...

...up and downvotes...

...agree and disagree votes...

...reacts...

...post mentions...

...and just the normal data of page views, comments written and so forth.

This can tell us a lot about what people are interested in and what writing they find important.

We can also look at more high-level patterns, like:

Who are users you tend to upvote but also disagree with?
Who are users who tend to upvote each other, and comment on similar topics, but haven't yet had a conversation?
What's a topic that people would really like to see discussed, and where you and someone you respect hold opposing views?

...and so forth.

I don't know what the right questions are. But I have a sense, a trailhead, that we're sitting on this incredible treasure trove of data. And thus far it has been almost entirely unutilised for building LessWrong features.

(Note: in doing this, I want to be careful to respect y'alls data. I wrote a comment below with my current thoughts and approach to that.)

What's even more exciting: suppose we're able to use entirely on-LessWrong data to find and suggest conversations that we feel are interesting and important. That will then cause more such conversations to happen. Which, in turn, generates more LessWrong data that we can look at to recommend new conversations.

It's a flywheel!

I'm excited to try spinning it.

Here is a link to the Dialogue Matchmaking page :-)