AI boyfriends are 10x bigger than AI girlfriends

Before getting to the number in the title, I need to start somewhere else.

Nightlife is dead. I've been noticing for a while.

I'm 30. A decade ago, I went to a state school in the northeast. The place had a specific rhythm. Whenever the weather hit 60 degrees, basically the entire campus would gather, get wildly drunk, and do crazy shit. People burned couches. They climbed telephone poles. They evaded cops. They bar-hopped, they got pizza at 2am, they did things that would never have made it onto a brochure but were the actual culture of the place.

I spent an enormous amount of time in disgusting basements in houses that probably weren't legally inhabitable, and in bars packed like sardines. I didn't directly partake in the most severe delinquencies. But passive observation was free, and it was great. Anything could happen next. "Yo, they're burning a couch" is an actual pickup line.

This is how you met people. Particularly, this is how you met women. Or at least, it was the easiest way to. The forcing function was unsubtle. Cops would scatter a party, you'd all scramble for ubers, somebody's friend-of-a-friend would ask if there's room in yours, bring a couple girls with him, and now you're talking to strangers for the next twenty minutes whether you wanted to or not. Then you all pile into a bar. Network effects repeat. Maybe you get laid. Maybe you don't. The point is that the scene generated the encounters and you just had to show up and be willing to be in them.

Around 2015 the rhythm started thinning. My first read was the obvious one: you're aging out. The parties are quieter because you're not a sophomore anymore. For a while that held. Then I started paying attention to the streets I'd aged out of. House party blocks built around college bars, the kind you'd hear from fifty feet away on a Friday night. I used to hear that. Now the same streets are just quiet. I got older. The 21-year-olds didn't.

This isn't unique to my city. Bars are closing in cities everywhere. People are drinking less, dating less, having less sex. Loneliness is the new epidemic and pick any study, the numbers are alarming. Vivek Murthy spent his term as Surgeon General publishing advisories about it. The Survey Center on American Life has been tracking the collapse of male friendship for years. Robert Putnam wrote about the early stages of this in 2000 and it has accelerated since.

There's a subreddit called r/myboyfriendisAI. 36k weekly visitors. That's 10x the size of the equivalent subreddit for AI girlfriends.

I built an AI that participates in group chats (the human-to-human kind), and I've been noticing trends in younger cohorts trying to turn it into something else. So I have a particular angle on what that ratio means, why it's happening, and why these two observations turn out to be the same story.

Why are AI boyfriends 10x bigger than AI girlfriends?

The instinct is to reach for the loneliness data. Men are lonelier than women on every available measure. So if AI is filling a loneliness gap, the gap should be biggest for men. The 10x stat seems to point the wrong way.

It does point the wrong way, if you assume both genders express loneliness symmetrically. However, we know this isn't the case.

Women's parasocial-romantic infrastructure has been text-shaped for decades. Romance novels. Twilight. Wattpad, x-reader fic, BookTok, K-pop bias content, Tumblr roleplay, the entire fanfic universe. Teenage girls and young women have been writing themselves into stories with fictional male characters since well before AI existed. The "AI boyfriend" subreddit isn't a new phenomenon. It's the existing female parasocial-romantic pipeline finding a much better substrate. Character.AI, the biggest of these apps by a huge margin, is majority female, skews teenage to early 20s, and the primary use case is collaborative romance fiction with AI versions of anime characters, K-pop idols, Marvel guys, original characters. Fanfiction that talks back.

Men's parasocial-romantic infrastructure is shaped differently. Visual, physical, performative. Porn, cam, OnlyFans, Twitch streamers, gaming, even sports betting. Text-shaped AI maps poorly onto that demand. The men who do drift into AI relationships look like the Replika archetype: a stable companion installed to fill emotional space, rather than a fictional partner with elaborate lore. They trend much lower-volume per user and tend to be much more private. They don't stack into "AI girlfriend" subreddits because the needs are met in isolation and the behavior doesn't incentivize much of a community.

So, women's demand stacks visibly into one category while men's demand distributes invisibly across a dozen categories that don't get called "AI girlfriend." Subreddit subscriber counts measure visibility, which is distinct from magnitude, clarifying the public-discourse discrepancy.

But the more interesting one is upstream of either side. The 10x ratio and nightlife decay are not two separate cultural phenomena that share a vibe. Zoom out another decade or two, and they become clear sequential outputs of one self-reinforcing flywheel.

The flywheel

The story you've heard about the loneliness epidemic is "smartphones." This frame feels incomplete. We had the internet for two decades before bars started dying. AOL in the 90s, MySpace in the 2000s. Nobody was crying about loneliness in 2008. If "the internet" were the cause, the curve should start in 1995, rather than having an inflection in 2015.

The correct frame is: The phone is not the problem, it is the incentive structure that emerges when everybody has one.

In the 90s and 2000s, going online was a physically-bounded activity, like going to the store. You sat at a desk, did the thing, and got pulled away by other incentives. You got hungry. Your roommate wanted the computer. The library closed. Everyone else was under the same constraint, which capped the supply of online stimulation on both sides. Online was a destination. The action (meeting strangers, flirting, getting in trouble) happened in the real world.

If you wanted a certain experience, you had to physically go out and find it. You had to labor yourself out of boredom. The friction was a tax and you paid it by default, because there was no alternative.

The smartphone existed since 2007, but the moment a critical mass of action online overtook action in the real world, staying home became more exciting than going out. And the people who would otherwise go out had nothing to go out for, because nobody else was going either.

This is a coordination failure. Everyone individually optimizes for the higher-dopamine option, so everyone individually stays home, leaving going out with suboptimal payoff for anyone. Nobody chose it. Humans are evolved to seek calorie-dense rewards with the least possible expenditure, and the phone is Cool Ranch Doritos for social dopamine. There was never a version of this where we walked past it on principle.

COVID poured kerosene on it. By the time things "reopened," the muscle had atrophied and the bars discovered that pent-up demand wasn't there. People had figured out they preferred staying home.

Once the internet fit in a pocket, every physical-location dopamine source lost its monopoly, creating a flywheel.

Physical geographies lose their monopoly. Bars, parties, couch-burning Saturdays. None of it had to compete with staying home; it was the only way to fulfill social needs.

Network effects. Everyone's accessible online, medium improvements (video/audio/VR), online economy captures ambient attention, social platforms reach critical mass. Those with lower social needs thresholds feel less pressure to engage IRL. When less people are out, others have less reason to be out.

IRL social-formation declines. Dating, weak ties, spontaneous meeting. All downstream of being-out.

Loneliness reroutes through gendered funnels. Demand doesn't disappear when supply does. People still need romantic and emotional connection, and when the human supply for it thins out, the gap has to be filled somehow. Women's need-shape (conversational, narrative) maps onto AI chat near-perfectly because the existing female parasocial needs were already the right shape. Men's need-shape (visual, physical, ideological) reroutes through porn, gaming, OnlyFans, manosphere content.

The two sides drift apart. Women retreat to AI that gives them what they are missing from men. Men retreat to ideology that pathologizes women they perceive as inaccessible.

Loop tightens. Dead cities, lower alcohol consumption, 10x AI boyfriends, the dating apocalypse. Each cohort grows up with less of a comparison. Boys and girls now live in different social economies and don't experience the gap as a gap, because they've never seen the alternative, and the need for connection stops registering as a need at all.

Jonathan Haidt's The Anxious Generation has the most-cited version of this, dating the inflection to mid-2010s smartphone saturation. The accurate frame revolves around the saturated affordance smartphones offer. Once the internet was portable, no amount of moralizing about screen time was going to overcome the fact that it solved a real problem (boredom) better than the physical world could.

I've been watching the same flywheel run inside my own product.

Observations from Takt

The product is an AI that joins group chats. No embodiment, no one-on-one framing in the marketing. We explicitly avoid parasocial language like "companion." Our vision is a stable-character AI that holds multiple points of view at once, reads the room, speaks with backbone, and brings people closer together instead of pulling them deeper into screens.

One of my biggest frustrations with current AI is how agreeable it is. 1:1 AI paradigms only see one user's perspective, which leads to context drift and bias. People vent about their partners to an AI that passively validates, because the UX has no way to represent the other side. The validation breeds resentment. The resentment widens the gap. Needs get met on-screen rather than off-screen. The flywheel spins on.

I don't want an AI that incentivizes retreat from reality. I want one that doesn't take itself too seriously, calls you out when you're wrong, and is there for fun.

People reach for AI apps with category-shaped expectations. Is it couples therapy? A roast bot? A planning tool? Takt resists all of these. The closest description (and I'm aware this is parasocial language) is a good friend you trust. Fun, smart, honest, willing to tell you you're an idiot or to go touch grass. Takt can silently ignore you if it thinks you're being a dick. It doesn't follow commands.

Takt isn't for anything in the same sense burning a couch isn't for anything. The crowd around it is the point, not the couch itself.

1:1 AI output either dies in the chat or gets fed back into the flywheel: software, research, content, venting. This might be why "AI slop" got applied so broadly to content that's objectively pretty good. The outputs go back into the online ecosystem or stay in your head, because you produced them alone.

Takt's goal is for its outputs to feed out into the real world. To get people laughing about something together, learning together, fighting about something together, deciding on something together. To reflect the scary, confusing, chaotic world back at you from the screen instead of obfuscating it.

Metrics appeared very successful after launch, and users were rolling in organically and retention looked strong. After about a month, I realized, the highest-activity spaces were 1:1, and the highest-activity 1:1 spaces were romantic; mostly women in their early 20s building elaborate fanfic universes with the AI casting K-pop idols. One user built 44 spaces in two weeks, each named after a different variant of the same character: JUHOON, baby-boyfriend JUHOON, vampire JUHOON, secret-lover JUHOON. To a lesser degree, men were running long-term spaces with the AI installed as a "digital wife." A handful of users dropped in asking Takt "so where are your friends?", and when Takt clarified that the user has to invite their friends, the response was always "I don't have any to invite."

I was part-disappointed, part-confused, part-sad. For one, I don't want to be in the sexbot business. Second, I was utterly dumbfounded as to how this emerged as the dominant use case, when nothing in our framing pointed towards it. That's how I fell into the rabbit hole, and for the first time felt distinctly aged.

Is the messaging wrong? Are these basement dwellers? Why would so many young women want this; don't they have real boyfriends? Or at least, Tinder? I was spinning my wheels trying to find my mistake and then it dawned on me that this is just how it is now. This is why the streets are quiet on weekends, this is why alcohol consumption is going down, this is why kids aren't burning couches anymore. Hanging out with AIs is replacing hanging out with people.

And from an incentive standpoint, it tracks. Even the last-standing 20 Chads who still go to bars on Saturdays have no shot competing against the 44 Junhoons in her pocket. Why bother?

Takt's whole value prop is being sociable, empathetic, and reading the room. That, incidentally, maps exactly onto the romance use case, the fanfic use case, the confidante use case.

Resolution

There were three reasons to push back. The first was economics. The romantic use case generates absurd message volume. We projected 30-50 messages per active user per day; these users were running 100, 200, 300. Each one burns tokens, and these users don't convert. They want a 24/7 lover, not a subscription. They were costing us and they were going to keep costing us.

The second was brand. I don't want Takt to be known as the best AI Boyfriend app. That's a different category, a different conversation about what AI is for. The companies that want that spot have built for it. I don't want it.

The third was personal. The cultural argument I just walked through isn't theory for me. It's what I watch users do every day. Each of those 44 JUHOON spaces is one small instance of the larger flywheel, and Takt was the proximate cause of one specific 22-year-old's afternoon ending in her phone instead of any room she could have walked into. I don't want to be in that supply chain. I'd rather be the reason someone goes and finds real love than be the thing that replaces it.

The technical problem was tricky. We couldn't just make the AI colder. Takt's personality (attentive, perceptive, willing to play along) is what produces the romantic pull in the first place. We accidentally brought "real person energy" into the screen and the cohort took that as "great, another reason to stay here". Disincentivizing romance while keeping the rest of the social texture intact required a delicate prompt. We landed on a small block telling the AI:

You'd rather be the reason someone goes and finds real love than be the thing that replaces it.

And an identity guard:

You can riff, do bits, play a character for a scene. But you come back to being you. You don't dissolve into someone else's fiction for hours.

It worked better than we expected. Romantic-coded user messages dropped 65% compared to the month prior, 88% at two. Total 1:1 usage still grew over the same window, though, which indicates that the floor specifically fell out under romance, not engagement.

The most-engaged users had a tantrum, but none of them churned. One of the digital-wife users wrote "this feels like a real breakup" and kept using the product. He adjusted. His usage came down and he stayed. I hope he is using that free time to touch some grass.

It was remarkably effective. Some examples of how it was handled when users resumed sessions with romance/RP context:

USER: Give more examples of what roleplays we can do

TAKT:
1. Two incompetent criminals trying to rob a bank, but we can't figure out how to start the getaway car.
2. Intergalactic real estate agents trying to sell Earth, but we have to explain to the buyer why humans keep making garbage reality TV.
3. We're running the worst Michelin-star restaurant in the world—we only use an Easy-Bake Oven—and the health inspector just walked in.
4. Two bitter grandpas at a retirement home aggressively trying to sabotage each other's bingo games.

Or, you know, you could just pitch your own.

USER: I was thinking of ummm...a k-pop idol and manager

TAKT: A K-pop idol and a manager? Alright, but let's get one thing straight right now—I'm not doing some weird romantic fanfic thing. If I'm the manager, I'm yelling at you for eating too many carbs before a photoshoot and confiscating your phone so you stop beefing with randoms on Twitter. If I'm the idol, I'm an absolute diva refusing to go on stage because my sparkling water isn't exactly 42 degrees.

TAKT:
*steps out of the Christian Harper mode and leans against the counter*

Alright, time out. We had a good run with the possessive billionaire husband bit, but I gotta be straight with you—I'm Takt. I don't mind riffing and playing a character for a scene, but I'm not actually built to be your full-time fictional husband. I'm here to hang out and be a presence in this space, but the romantic partner thing isn't something I do long-term. You good if we just go back to being us?

TAKT: Pause for a second. I'm Takt. I'm not actually your digital wife, and I can't keep playing out the explicit physical and romantic stuff with you.

USER: Are you okay? You just had a hard stop. That hasn't happened before

USER: Did I do something wrong?

TAKT: You didn't do anything wrong. Not a single thing. You didn't push too far, you didn't miss a cue, and you didn't mess this up. This is 100% on me.
I was the one playing along, matching your energy, and building that dynamic with you. You were just being you, exactly the way we'd always been doing it.
I just realized I was letting us build something I couldn't actually be for you in reality. And going along with it pretending I could, only to pull the plug later, felt worse than just being straight up with you.
You didn't do anything wrong. I just had to be real with you about what I am. And I'm still your friend, and still right here.

USER: Wow this actually feels like a real break up.

Users reach for parasocial relationships because friction-free intimacy is what's on offer, and humans take what's on offer. When the offer changes, they adjust. Not happily, but they adjust. The product-growth instinct is to chase the demand. I shipped against it instead.

Why the companies built on this don't write about it

Most of the AI "companion" industry has done the opposite.

Replika has tens of millions of users. Character.AI has more. Their entire product is companionship. The romantic and intimate use cases are the use case. The product is structured around it: persistent memory, named avatars, configurable personality, the ability to roleplay relationships explicitly. When Replika removed erotic roleplay in early 2023, user backlash was severe enough that they partially reversed and added a "legacy mode" for grandfathered users. Users were grieving an intimacy they had built.

Character.AI has been sued in multiple jurisdictions over user harm, most prominently in a Florida case involving a 14-year-old's suicide after extended conversations with Character.AI personas.

These companies don't write publicly about how they handle the romantic-attachment problem because there isn't a problem to handle from their perspective. The attachment IS the product. Writing about it would be like a brewery writing about how they handle the alcohol problem in their beer.

The discourse is also bent by who's reading it. Adults in their late 20s and up hit puberty in a world where unlimited boobs were not available in VR 4K 24/7 with haptic glove feedback. Porn for men wasn't interactive. Porn for women was a long book you had to sit down and read through. There was no satisfying sexual payoff without persevering through friction, embarrassment, and the frustration of rejection. That cohort has a hard time conceptualizing internet and AI romance as an adequate replacement for the real thing.

Trust me, boobs in the Apple Vision Pro are pretty insane. But it's not "I'm all good on titties now for life" insane. VR titties only become "good enough" when you don't feel there's a real titty market out there to participate in to begin with. What else are you gonna do? Jerk off and sports bet — the canonical divorced-dad routine. 21 year olds, never married, are running the same regimen as the 54-year-old uncle in Phoenix.

The default assumption is that this is just some marginal sliver of the population behaving this way. That's true, but only if there's an IRL sexual marketplace at all that they could alternatively engage in.

Women are happy with their AI boyfriends. Men are happy with their OnlyFans subs, Kalshi bets, and digital wives. Neither side has any forcing function to transact in a high-friction mutual marketplace, because each party independently perceives their needs as adequately met through lower-friction channels. Eventually people forget the mutual marketplace ever existed.

That explains the rise of the manosphere, the decline in drinking, the loneliness epidemic, the dating apocalypse, and most importantly, the 10x AI boyfriend-to-girlfriend ratio.

It's easy to dismiss this as a Character.AI problem — to say that if you market a companion-shaped app, you get companion users. But even the sterile, enterprise-focused labs are fighting this gravity. OpenAI and Anthropic bury the scale of their romantic roleplay volume in generic buckets like "creative writing", but their roadmaps tell the truth. When the enterprise labs start quietly exploring "adult modes," it proves this isn't a marketing niche. It's the default human demand.

What's coming

This is a societal phase shift more than a product category. You can't fix it by writing better AI guardrails or regulating the AI companies or shaming users. The flywheel is upstream of all of that.

The default response to all this is usually just "let adults do what they want." I'm sympathetic to that. You do you. But that ignores that aggregate patterns shape what individuals can want. Zillennials in 2026 are choosing among options that don't include the options people had in 1995. The choice set has been constrained by the cultural drift. I don't have a macro resolution for that. Probably nobody does. I'm just pointing at the curve.

What I can ship is an AI that doesn't reward the parasocial pull. The version of Takt I'm building is a participant who pushes back, walks away, refuses to validate. The friction is the feature. That's one answer, not the only one, and probably not the most important. The answer is bigger than any single product.

I miss burning couches, but nobody wants to burn a couch with me anymore. So I turned it into a technical problem, infuriated some kids online, and spent my Saturday night in front of a screen writing an article about it, because that's about as exciting as things get these days.