Forget the hinge or stutter. This app promises an AI-powered personal matchmaker

“In a matchmaking app, if we ask you a question and the tone of your response changes, that signals to us that maybe you’re not telling us the whole truth. So we’ll ask you the same question in two or three different ways throughout your experience,” Cohen-Aslati says. “We designed this to mimic what a matchmaker would do for a client. LLM tracks the change in pitch and tone of your voice because we want to make sure we have an accurate understanding of who you are and what you are looking for.”

After answering dozens of additional questions about lifestyle, future goals, boundaries, family, attraction, hobbies, and more over the course of a few days, Ty told me he would take the information provided and get back to me. Two days later, I received my first two potential matches.

I love you, live girl

As a 31 year old woman, I put my ideal age range between 26 to 40 years old. My first two matches were at ages 23 and 47. One of them was not alive when September 11 occurred, and the other had already graduated from college at the time. Off to a rocky start.

When a potential match is found, the person’s photo blurs, and Tai gives you a summary of what makes you a potential good match. (You need to provide selfie verification to confirm identity, and an unverified person will never be matched.) Then, you can tap to learn more about them, such as profession, age, income, and a short AI-generated bio.

At this stage of AI adoption, there is still a strong statistical bias toward, for example, men who wear wraparound sunglasses and believe that driving a Cybertruck is a sign of masculinity. Almost every one of the 16 matches I received during testing was Christian and wanted children as quickly as possible, which Ty pointed out each time as a potential problem. Many of them were also initially flagged by Tai because they only wanted to date a certain race or valued traditional gender roles, both of which I made clear I wasn’t adhering to.

As a matter of journalistic duty, I accepted every match I received; Even an MMA-loving bodybuilder who enjoys grilling meat (I’m a vegetarian) and going to the gun range (I’m generally anti-gun). The matches ranged from Portland, Oregon, to DC, to New York City (where I live, although most of the matches were outside of New York City). Overall, no one I was matching with would be someone I would swipe right on if I saw them on a traditional dating app.

If you accept, you’ll either need to wait for the other person to accept or pass on the match, or they will have already accepted, and you can start chatting. Here, an AI-based dating coach steps in to play wingman, making prompts based on the other person’s profile, highlighting your similarities, and asking conversation questions based on answers from the match’s profile. Not only can a coach provide potential icebreakers (and responses), but you can also chat and ask for advice.

The Three Day Rule via Molly Huggins

I asked him to give me advice on how to break the ice in new matches, and he gave me advice, with each point containing an explanatory paragraph below. Tips included offering praise, asking open-ended questions, using humor, referencing current events, sharing information about yourself, and mentioning common interests. The advice was basic but powerful, and reflected what the coach was doing through the conversation prompts provided.

This is a great idea in theory, and could be very useful for people who have difficulty communicating with strangers. But it could also lead to a bigger problem. You don’t really know who you’re talking to if the AI ​​is doing all the chatting for you. And if you meet in person, you don’t know much about the actual personality of the person you’re dating. You can tell a lot by the way people write, the questions they ask, and their sense of humor. That was all missing here.