A Research Program
The hypothetical point at which computational models of human personality reach sufficient resolution that relationship outcomes become predictable before two people ever meet. Not a dating app. A research frontier.
We are living in a social dark age. Married people report happiness equivalent to a $50,000 salary increase. Finding a one-in-a-million match instead of one-in-a-hundred doesn't make someone a little happier. It satisfies something at the level of the soul. The goodness of relationships follows power laws, and we have almost no infrastructure for navigating them.
The Big Five personality model is a 5-pixel image of a person.
Before CLIP, computer vision meant classifying images with a handful of hand-labeled features. After CLIP, every image on earth could be embedded in a single space at whatever resolution was needed. The same transition is coming for human personality, and it changes everything about how we find the people we're meant to know.
This is not speculation. Alan Cowen at Hume AI already proved the paradigm for human emotion: unsupervised high-dimensional representations recover structure (like awe vs. surprise, or nostalgia vs. melancholy) invisible to prior label-based frameworks. We are extending this to personality, and from personality to relationship outcome prediction.
This research program lives across several venues. Here’s where the work is happening and how to participate.
A conference in San Francisco exploring the intersection of technology and human connection. Covered by The New York Times.
symposium.love →AI for Human Connection: From Matching to Flourishing. Personality embeddings and relationship outcome prediction for the ML community. Sydney, December 2026.
Workshop details →Live experiments in AI-mediated connection. Participate in research studies, try personality embedding tools, and contribute data.
experiments.dating →Researcher, co-organizer, speaker, industry partner, or just curious? Book a conversation about the research program.
Book a time →Each represents a tractable first experiment with existing data. Together they form a path from personality measurement to relationship prediction.
Unsupervised, high-dimensional, multimodal personality vectors learned from text, voice, video, behavior, and digital footprints. If I can predict every token you'd generate, I have a model of your personality. The conditional embedding is the personality.
All important personality trait combinations eventually become tropes in a culture's stories. TV Tropes is a bipartite graph of characters and tropes, effectively unsupervised personality clustering by thousands of human editors. Node2Vec on this graph produces a character embedding space where similar characters cluster. The training data already exists.
Compatibility is not a number. It's a structured manifold: a probability distribution over the kinds of relationship dynamics two people will discover. A compatibility score is to a relationship outcome manifold as a temperature reading is to a full weather model.
Alan Cowen's work at Hume AI proved this paradigm for emotions. Self-reported labels are a lossy pre-CLIP taxonomy. Unsupervised representations recover structure invisible to prior frameworks. If it works for emotion, it works for personality. The style-GAN moment is imminent.
Generate the manifold of all possible faces, walk users through latent space to map aesthetic preferences, and identify regions of high mutual attraction that neither person would have found by swiping. High-variance appearance gets more messages than high-average. The alpha is in the tails.
Embed two personalities as conditional prompts for language models. Monte Carlo simulate their conversations, conflicts, and resolutions. Run 10,000 dates before the first one. Generative agents in a town was a proof of concept. The next step is generative agents in a relationship.
Two hours covering personality embedding spaces, the Cultural Trope Hypothesis, Cowen's emotion manifolds, Moneyball mutual attraction, LLM relationship simulation, geographic optimization, and the path forward.
The full theoretical framework for personality embeddings and relationship outcome prediction. Download PDF →
We formally introduce Relationship Outcome Prediction (ROP) as a distinct field within computational social science and machine learning. While traditional link prediction focuses on the binary existence of edges, and affective computing monitors transient emotional states, ROP addresses the longitudinal trajectory, stability, and terminal status of dyadic systems.
We propose Deep-ROP, a unified architecture integrating three innovations: (1) P3HF, a personality-guided hypergraph transformer that disentangles public interactions from private psychological states; (2) TempODE, a continuous-time dynamic model governed by Allen-Cahn phase-field potentials to capture the non-linear stability of social bonds; and (3) RELATE-MACT, a generative simulation engine utilizing collaborative LLM agents to model counterfactual “turning points” in relationship trajectories.
We posit that relationships exist in a state space defined by a scalar order parameter φ ∈ [-1, 1], with social potential energy as a double-well potential — two stable states (commitment and dissolution) separated by an energy barrier. Ambiguity is unstable. Relationships naturally slide toward one well or the other.
Matthew Fisher on the Vectors of Mind podcast with Andrew Cutler. 50 minutes on personality embeddings, the Cultural Trope Hypothesis, and the research program behind the Relationship Singularity.
The New York Times’ flagship podcast explores the end of the swipe era — featuring AI-driven matching and the research behind the Relationship Singularity.
New York Times “Can You Optimize Love?” (January 2026) The Daily (NYT) “Is the Swipe Era Over?” Paper A Theoretical Roadmap to the Relationship Singularity YouTube Full 2-hour research talk, Love Symposium 2024 Podcast Vectors of Mind, “AI, Dating Apps, and the Future of Relationships” Conference Love Symposium, San FranciscoThe research program draws on work across representation learning, computational social science, personality psychology, and affective computing.
Representation Learning
Emotion & Affect
Personality & Social Prediction
Social Simulation & Agents
Data Sources
This Research Program
Matthew Fisher is an AI researcher working on personality embeddings and relationship outcome prediction. He co-founded the Love Symposium in San Francisco, a conference exploring technology and human connection covered by The New York Times.
His research draws on representation learning, computational social science, and the hypothesis that human personality can be embedded at arbitrarily high resolution, and that relationship outcomes between any two embedded personalities can be predicted as structured distributions, not scalar compatibility scores.