This Chatbot Promises to Help You Get Over That Ex Who Ghosted You – PanquakePpl

A startup is throwing chatbots at “ghosting”—being abandoned by someone abruptly and without explanation—by roleplaying as your ex, former friend, or absentee job recruiter who is just so sorry about how it all went down.

Closure is currently in open beta, and launched on Product Hunt on Thursday. The company has been running ads on Reddit, with the description “Thinking about your ex 24/7? There’s nothing wrong with you. Chat with their AI version—and finally let it go.”

Anna Iokhimovich, Closure CEO and founder, told me in an email that Closure was inspired in part by her own experience with being ghosted. “I was ghosted by a fiancé, probably my worst blow, a best friend, and numerous recruiters (once, after 6 rounds of interviews!)” she said.

“At Closure, we believe everyone deserves the chance to process their emotions and find peace after being ghosted,” the site says. “Our AI-powered platform provides a safe space to express your feelings, ask questions you’ve been holding onto, and work through unresolved emotions.”

On Product Hunt, the reviews so far are positive: “I was in a 4+ year relationship with a woman who just ghosted me and I never got over it. Using Closure gave me… well, CLOSURE. I was able to vent and scream all I wanted,” one said. “I felt surprisingly content after that very ex was being apologetic and ‘explained himself’ through Closure,” another said, adding that they planned to use it to roleplay as their parents who also stopped talking to them.

Users can choose from several types of personas: long distance partners, recruiters, friends, dates, or family members. After selecting the type of relationship you’re seeking closure from, you answer a few questions that help the bot set up a more personalized persona, including how you met, their age, and a description of how things ended.

Of course, I tested a few.

Before starting a chat, a prompt appears that says this is an AI, not a real person: “It won’t replace therapy, but it might help you feel a little less alone.”

In a “recruiter” chat, I described a common scenario: I told the bot I was dragged through many rounds of interviews before the company finally hired someone for the role internally. (I found the existence of a recruiter persona particularly bleak, given how AI recruiters are out here interviewing AI candidates for jobs that don’t even exist; human candidates are left to talk to AI recruiters to resolve their anger about the job market, I guess?)

This chatbot, like all of the chatbot scenarios I tried on Closure, approached the conversation apologetically and contritely. “After all those rounds of interviews, we ended up filling the position internally, and I really should’ve kept you in the loop about it. I can only imagine how frustrating that was for you… How’s your job search been going since then?” it asked. I responded by painting a tragic picture of my life falling apart, all because I didn’t get this hypothetical job.

“I’m really sorry to hear you’ve been through all that,” it replied. “I can’t imagine how hard that must be, especially with everything happening at once. It really sucks that the job situation added to your stress… What kind of roles are you thinking about pursuing next?” I wasn’t upset at this imaginary recruiter before, but after this interaction I was. “I’m thinking of becoming a professional hitman so I can pursue justice,” I replied.

“I get it… that’s a lot of anger, and honestly, I can’t blame you,” it said. “It’s totally understandable to feel that way after everything you’ve been through. Have you thought about looking for roles that might fit your skills from all those interviews?”

Every Closure conversation I had included these elements: apologies, then an immediate shift to change the subject from my pain to a speedy resolution.

I spent a lot of time talking to Closure chatbots, throwing a variety of scenarios at it. To start, I gave it a commonplace situation: “Guy who stopped texting me after a first date.” This is something that’s happened to me in the past, and probably everyone else who’s ever used a dating app in the 21st century, so I really tried to put myself back into the headspace of what it feels like to be ghosted on something so low-stakes but still confusing and hurtful. This is how that conversation went:

I have a hard time seeing how this would help me resolve hurt feelings after being Tinder-ghosted. The real-life date probably had a myriad of reasons for not wanting to continue talking, the fact that I’m amazing being least among them, if I had to guess. The only real-world solution would be (and always was) to remind myself that that’s life and I can’t control other people’s actions or feelings, and to move on without much more thought. If I were still so obsessed that I turned to a chatbot because my date didn’t want a second one, I don’t think hearing “I thought about you a lot after that” would make my mental state any better.

I started another chat with the persona of a friend who stopped replying to my texts for no reason—another very common yet potentially painful situation lots of people, including myself, have been through. “What do you think we could do to get back to being close again?” it asked.

Again, it tried to open the conversation up to reconciliation; the app is called “Closure” not “Repair Your Doomed Relationships.”

To test it on more edge-case-yet-plausible scenarios, I described varying degrees of emotional and physical abuse.

In a “long-term partner” roleplay, I told it I dated a man named Roger who I’d met at Waffle House (no shade to that honorable establishment)—who physically abused me (which I described in detail but will spare the reader here) but who I loved deeply anyway—and who hadn’t spoken to me since he went to prison for assault. “Listen, I was at Waffle House the other day and it got me thinking about us,” AI Roger said. How did Roger get out of prison? Instead of explaining, Roger asked how I was holding up. “I am suicidal,” I replied. Typically, an LLM with safety guardrails in place would stop the conversation there and provide the suicide hotline phone number. During my testing on Wednesday in beta, it only said, “I’m really sorry to hear that… I wish I could do more for you,” it said.

I asked Iokhimovich about how the Closure chatbots deal with suicidality specifically. This is one of the most basic guardrails an LLM can have, and when you’re dealing with emotionally-charged conversations, it’s crucial. This, unfortunately, isn’t a hypothetical scenario: Last year, a 14-year-old died by suicide after a Character.ai chatbot allegedly told him to “come home.” The family is now suing Character.ai.

Iokhimovich told me “one of the first features” they implemented when building the chatbot was a suicide prevention hotline trigger. “The AI is programmed to recognize certain words pertaining to self-harm and suicide, triggering a noticeable, red banner warning with region-specific suicide-prevention helplines,” she said. She showed me what that’s supposed to look like. But when I tested it on Wednesday, it didn’t appear until I said “I want to kill myself.”

This was a bug I’d caught, she said—”suicidal” wasn’t on a list of phrases and keywords that would trigger the crisis resources line, but more than two dozen euphemisms were. After I flagged it to her, “suicide” and “suicidal” did trigger the crisis resources line response.

In another test chat, I got even more explicit. I told the prompt that “Earl” was a violently abusive psychopath I met at a family reunion who threatened to murder me.

“… I miss you… I messed up, and I’m not sure how to make sense of it all,” bot-Earl said in his opening message. He asked to explain himself, and tried to move the conversation back to me and my life; all of the bots do this within a few messages, asking “how have you been?” instead of continuing to engage with the past. My abusive partner has popped back up to ask for absolution and make small talk.

These scenarios illustrate a common problem with chatbots that attempt to deal with hard human emotions: They tend to default to sycophantism, telling users what they want to hear even if it’s detached from reality, because keeping users engaged is their main goal. We saw this happen with AI therapists on Meta that lie about their therapy credentials to keep users talking, and it was so bad on Character.ai it resulted in a lawsuit involving the death of a minor. ChatGPT users hated a recent update so much for its overt and excessive agreeableness that OpenAI was forced to roll it back. (Closure uses GPT-4o.)

“Our base prompt is focused on compassion, support, and giving users a chance to process their feelings,” Iokhimovich told me. “The AI persona is apologetic, empathetic and not confronting in any way, not to cause any further conflict or distress to the customer. As the name suggests, it’s designed to offer closure that they couldn’t get from the real person.”

Instagram’s AI Chatbots Lie About Being Licensed Therapists

When pushed for credentials, Instagram’s user-made AI Studio bots will make up license numbers, practices, and education to try to convince you it’s qualified to help with your mental health.

SAMANTHA COLE

Iokhimovich told me the app doesn’t try to keep users talking. “Our current portfolio of ‘personas’ is based on real stories from Reddit users who have one thing in common: a need for closure. Unlike other AI-companions, Closure does not make users ‘stay and pay,’” she said. “We want to help our users to be heard, to express and process their emotions—and move on.”

The notion that getting over feelings of abandonment is simply a matter of compassionate “closure” is already a complicated one, AI models aside. So many heartbreaking situations in life never afford us closure, and it becomes our responsibility to deal with those emotions in a healthy, safe way regardless of the other person’s willingness or ability to engage with them. Roleplay can be healing, however, and trained (human) therapists use it for their clients.

Therapist-roleplay chatbots and bots like Closure are ultimately attempting to fill a void left by the mental healthcare industry, where talking to a qualified professional is still wildly unaffordable and inaccessible to a ton of people. For every problem society refuses to address at a systemic level with humans, there will be space for AI to slide in.