When friends ask me to matchmake them, they usually list traits they want: "Kind, curious, growth-minded..." (Sometimes they even write date-me docs!) But I find it really hard to think of the right people from these descriptions.

Here's what I'm exploring, and suspect works better: "You know [person]? Do you know anyone kinda like them?" (Where "person" could be their ex, or that close friend they wish they were attracted to.)

Matching by description is hard. When someone lists desired traits, I need to:

  1. Understand what they mean by each trait
  2. Think of people I know
  3. Check if they match
  4. Somehow weigh everything together

But when I meet their person, I instantly get it - their vibe, how they talk, their humor, how they move through the world.

Plus, there's usually a gap between what people think they want and what works for them. Their trait list comes from trying to rationalize past attractions and guess future ones. But seeing who they've actually had chemistry with shows me what actually works.

An example also captures subtle compatibility factors they might not even be aware of. Maybe they say they want someone "growth-minded," but what they really click with is a specific style of playful intellectual banter that's hard to describe but easy to spot.

I've recently started trying to match people this way, with varying results. Would love to hear if others have successfully done this before!

I just wish I knew how to make this scalable (like, how do you do this on the internet?) or work even when you don't know the example person that well. If you have ideas, let me know!

New Comment
4 comments, sorted by Click to highlight new comments since:

A super silly heuristic I often use is "What media do you consume?". Intuitively, it kinda make sense as a sort of an informational parallel to the old adage "You are what you eat." Look at their spotify/RSS/blogging/shortform-video consumption habit tends to inform me whether A or B would at least have a decent first conversation. But this seems much better at matching friends than partners - presumably common interest and shared consumption of information is a slightly less important factor in continued romantic life (because there are so many other things!). 

This makes sense for the most part.

It's I portant to distinguish between chemistry and fit as a partner.

If someone says they want, for instance, a partner with a growth mindset, they can be totally right that that's the best partner for them, while totally wrong that they'll find such a person immediately attractive. They might be wildly attracted to some set of traits correlated with a fixed mindset.

They should still probably date the person with the growth mindset. Or at least choose consciously. The people they're attracted to might make them miserable in the longer term by being bad fits on important qualities like mindset.

Good chemistry can be bad for long term happiness; people wind up attracted to and in love with someone that's bad for them.

Perhaps there could be a way to efficiently measure similarity between people, without relying on vibes. Something like, measure everyone on hundred different scales (have them answer a questionnaire, have an LLM analyze their free texts), then say something like "this and this person seem similar to me", "this and that person do not seem similar". The system would figure out which dimensions you care about, and then find in a database the people most similar (in the dimensions you care about) to the one you want.

I just wish I knew how to make this scalable (like, how do you do this on the internet?) or work even when you don't know the example person that well. If you have ideas, let me know!

Immediate thoughts (not actionable) VR socialisation and vibe-recognising AIs (models trained to predict conversation duration and recurring meetings) (But VR wont be good enough for socialisation until like 2027). VR because easier to persistently record, though apple has made great efforts to set precedents that will make it difficult, especially if you want to use eye tracking data, they've also developed trusted compute stuff that might make it possible to use the data in privacy-preserving ways.

Better thoughts: Just a twitterlike that has semi-private contexts. Twitter is already like this for a lot of people, it's good for finding the people you enjoy talking to. The problem with twitter is that a lot of people, especially the healthiest ones, hold back their best material, or don't post at all, because they don't want whatever crap they say when they're just hanging out to be public and on the record forever. Simply add semi-private contexts. I will do this at some point. Iceshrimp probably will too. Mastodon might even do it. X might do it. Spritely definitely will but they might be in the oven for a bit. Bluesky might never, though, because radical openness is a bit baked into the protocol currently, which is based, but not ideal for all applications.