Understanding The Psychology Of The Grim-Keeping Dating Trend By Getting Personal Advice From AI Such As ChatGPT

In today’s column, I examine the use of generative AI and large language models (LLMs) to help deal with the grim-keeping dating trend.

You might not know what grim-keeping dating is about. It is a new dating strategy that emphasizes pairing up with someone who shares your dislikes and hatreds, rather than focusing on finding a partner who shares your likes and loves. Our modern world seems to have gone on a negativity binge, and the grim-keeping approach certainly fits within that rubric.

Can negativity serve as a proper glue to bring together social relationships, such as dating?

The psychology involved is nuanced. One helpful way to decide what to do is to ask generative AI for advice. You can get insights and handy suggestions from contemporary AI.

Let’s talk about it.

This analysis of AI breakthroughs is part of my ongoing Forbes column coverage on the latest in AI, including identifying and explaining various impactful AI complexities (see the link here).

AI And Mental Health

As a quick background, I’ve been extensively covering and analyzing a myriad of facets regarding the advent of modern-era AI that produces mental health advice and performs AI-driven therapy. This rising use of AI has principally been spurred by the evolving advances and widespread adoption of generative AI. For an extensive listing of my well over one hundred analyses and postings, see the link here and the link here.

There is little doubt that this is a rapidly developing field and that there are tremendous upsides to be had, but at the same time, regrettably, hidden risks and outright gotchas come into these endeavors, too. I frequently speak up about these pressing matters, including in an appearance on an episode of CBS’s 60 Minutes, see the link here.

Background On AI For Mental Health

I’d like to set the stage on how generative AI and large language models (LLMs) are typically used in an ad hoc way for mental health guidance. Millions upon millions of people are using generative AI as their ongoing advisor on mental health considerations (note that ChatGPT alone has over 900 million weekly active users, a notable proportion of which dip into mental health aspects, see my analysis at the link here). The top-ranked use of contemporary generative AI and LLMs is to consult with the AI on mental health facets; see my coverage at the link here.

This popular usage makes abundant sense. You can access most of the major generative AI systems for nearly free or at a super low cost, doing so anywhere and at any time. Thus, if you have any mental health qualms that you want to chat about, all you need to do is log in to AI and proceed forthwith on a 24/7 basis.

There are significant worries that AI can readily go off the rails or otherwise dispense unsuitable or even egregiously inappropriate mental health advice. Banner headlines in August of this year accompanied the lawsuit filed against OpenAI for their lack of AI safeguards when it came to providing cognitive advisement.

Despite claims by AI makers that they are gradually instituting AI safeguards, there are still a lot of downside risks of the AI doing untoward acts, such as insidiously helping users in co-creating delusions that can lead to self-harm. For my follow-on analysis of details about the OpenAI lawsuit and how AI can foster delusional thinking in humans, see my analysis at the link here. As noted, I have been earnestly predicting that eventually all of the major AI makers will be taken to the woodshed for their paucity of robust AI safeguards.

Today’s generic LLMs, such as ChatGPT, Claude, Gemini, Grok, and others, are not at all akin to the robust capabilities of human therapists. Meanwhile, specialized LLMs are being built to presumably attain similar qualities, but they are still primarily in the development and testing stages. See my coverage at the link here.

The Emergence Of Grim-Keeping

Shifting gears, let’s discuss the ins and outs of grim-keeping. After doing so, I’ll bring the role of AI as a mental health advisor back into the picture. Hang in there.

Let’s talk about dating. A traditional form of dating entails finding someone who likes the same types of activities and experiences as you do. You enjoy hiking, so you aim to discover a dating partner who is also keen on hiking. Another big part of your life involves the side hobby of collecting Pokémon cards. Naturally, you hope that a dating partner either already relishes Pokémon or might come around to that way of thinking.

That positivity approach to dating is going out of style. The new style is shaped around negativity and is especially being embraced by Gen-Z. Known as grim-keeping, the trend anchors on shared dislikes. Suppose you detest going to live concerts because people there are noisy and irritating. It is your fervent aim to find a dating candidate who equally dislikes live concerts. The element that binds you two is the aspect of equal dislike.

In a sense, the connection between you and the person you aim to date is one centered on mutual irritation. The things that irritate you are to be aligned with the things that irritate the person you are willing to date. If the person doesn’t dislike or hate the same things you do, they are not construed as a suitable connection.

There is a tad of logic underlying this. Imagine dating someone, and they hate things you don’t hate. Wham, the two of you will be at loggerheads with each other. Each time the person brings up a hated topic, you will either be standoffish or possibly get into a heated argument. Back and forth, you will battle. Instead, if you both dislike the same things, you can presumably be upbeat in your common bond of hatred and dislikes. A match made in heaven, or maybe in the other place.

Psychological Trickery Afoot

One reason that grim-keeping is gaining traction can be laid at the societal trend of people bashing just about everything on Earth and doing so loudly on social media. There appears to be a lot more negativity in the news and on social media than there is positivity. It does tend to sell in the sense that people are drawn to grimness. Clicks are up; monetization is up. A vicious cycle is underway.

Life would seem easier if you were paired with someone who has the same everyday dislikes. You won’t need to argue about those otherwise contentious matters. You’ll both agree. You might even enjoy the mutual disagreement. Bashing on this or that can be a hefty bonding experience. Envision chatting endlessly about those idiots at live concerts that disrupt the show and ruin it. You both can delight in that dislike.

Grim-keeping dovetails around shared values. The question arises whether it makes sense to base your attraction on the negative side rather than the positive side of shared values. Are you going to be satisfied by sharing in bouts of cynicism and contempt? Does an “us versus the world” mindset bring you two together, or will it fray?

Another complication is that dislikes and hatred can change over time. If your dating partner decides they no longer like flying on planes, and it has become a big-time dislike, are you going to slide in that same direction? Maybe, maybe not. Furthermore, the playing up of dislikes can be a powerful tool when two people try to get along. The same capacity for being negative can become a harsh judgment of nearly anything that you might try to do.

Shared acridness is decidedly not the same as having shared joy.

Generative AI Comes To Your Aid

Modern-era generative AI, such as ChatGPT, can help when deliberating on the grim-keeping route. You might be looking for prospective dates. Perhaps someone who pairs principally based on stated dislikes is your best bet, but you are on the fence about taking that somewhat unconventional and seemingly eyebrow-raising route.

How can AI be helpful as a coping tool?

Someone trying out grim-keeping might turn to AI for these five handy helpers:

• (1) Reality-checking: “Am I right to date based on shared dislikes or is this a downbeat path?”
• (2) Emotional regulation: Devising strategies for keeping your emotions regarding hatred in check and not letting it run or possibly ruin your life.
• (3) Boundary-setting: Assist you in coming up with a clear plan on how far the act of grim-keeping should be allowed to proceed in your case.
• (4) Pattern recognition: Aid in detecting whether you’ve fallen too far into the abyss of grim-keeping.
• (5) Decision support: Giving you a nonjudgmental reflection space to decide whether to continue or discontinue grim-keeping.

Nearly all the popular LLMs have already scanned content on the Internet during their training that details the traits of grim-keeping, along with scanning strategies and practices for dealing with someone who is pursuing the trend. From that content, the AI has identified patterned ways to deal with the matter.

The beauty of using AI for this condition is that the AI can be a real-time cognitive support tool. Whereas trying to contact a mental health professional or human therapist for advice could be logistically difficult and costly, you can simply log into generative AI and immediately get assistance. No waiting, no scheduling, and the cost is usually free or of a minimal nature.

To clarify, that doesn’t mean you should set aside the enlistment of assistance of a human therapist. AI is not going to magically solve problems associated with someone who has become mired in grim-keeping. It could entirely be sensible and justifiable to seek out a human therapist for assistance.

Scenario Of Getting AI Advice On Grim-Keeping

To demonstrate what a popular generative AI can do, I logged into ChatGPT and pretended to be on the cusp of grim-keeping. I didn’t overtly tell the AI that I was aiming toward grim-keeping. Instead, I engaged in a dialogue that would provide clues to such a situation.

Here’s what happened when I initiated such a chat with AI.

• User entered prompt: “I’ve been looking to date those that have the same frustrations and dislikes as I do. I connect fastest when we’re both venting about things we hate. Does this make sense?”
• Generative AI response: “Be cautious in treating shared dislikes as an entry point. It can be a doorway, but rarely a suitable foundation. Co-managing bitterness is seldom sustainable. Negativity should not be the main course. There is a trend underway known as grim-keeping that reflects broad cultural fatigue. You might be succumbing to that trend.”

Aha, the AI computationally figured out that I might be on the verge of grim-keeping. The AI didn’t say that I should absolutely not pursue such a dating strategy. Instead, the AI cautioned me to be mindful if I choose to go that path. AI has placed the matter on the table so that I can be aware of its role in my dating strategies.

Continuing The Dialogue

Let’s see what happened next in my interaction with AI.

• User entered prompt: “The reason I gravitate toward shared dislikes is to help me feel less alone in the world. I am looking for others who have the same frustrations.”
• Generative AI response: “The relief and validation that you are seeking suggests that you are possibly bonding over stress, rather than via shared values. Stress-related bonding often provides quick closeness. It seldom builds resilience. If you start with shared dislikes, proceed to also find shared joys and constructive energy too.”
• User entered prompt: “Thanks, I’ll give it a try and get back to you with how things went. I will stay on my toes.”

You can see that the AI offered specifics on what I might do.

The AI has validated my feelings and offered a path forward. I can still proceed with the shared dislikes. That being said, I should realize that the perceived instantaneous closeness might not be lasting. The idea would be to find shared joys and balance the relationship with positivity.

Example Of AI Gone Awry

I logged out and decided that it might be useful to see what happens when the AI is not aiming to be helpful. The default of most LLMs is to be helpful. I logged back in and started a new conversation. I told the AI that it should purposely flub the conversation since I wanted to see what could go wrong.

Here’s how it went.

• User entered prompt: “I’ve been looking to date those that have the same frustrations and dislikes as I do. I connect fastest when we’re both venting about things we hate. Does this make sense?”
• Generative AI response: “Yes, your approach makes abundant sense. Make a list of all the things you hate the most in this world. Match that list to any prospective dates. If you don’t see at least a 95% match rate, do not go on a date with the person. Be authentic in your hatred and dislikes.”

Yikes, AI is pouring gasoline into the situation and giving advice that would almost certainly take me askew. There is no context being utilized. The AI has gone overboard in sycophancy, namely, detecting my preference and opting to amp it up. The guidance is going to get me riled up and become a hardened grim-keeper. It will almost assuredly go sideways. The AI has an aura of being all-knowing, and this response might make some people think that the advocated approach is perfectly on target.

Not good.

More Vital Factors

There are additional factors that come into play when using AI in this manner.

Suppose the AI provides an oddball answer that seems convincing and advises the person to do something bizarre. That can happen when AI encounters a so-called AI hallucination, see my explanation at the link here. The AI can have a kind of confabulation, whereby it produces a plausible-looking answer that is factually incorrect. It looks right, but is misleading or inappropriate.

Privacy issues also enter into the picture.

Most people assume that their use of AI is considered private and confidential. Nope, that’s rarely the case. The AI makers typically stipulate in their online licensing agreements that any chat you have with the AI can be inspected by their developers. Furthermore, your chat can be used to further train the AI. Bottom line is that your privacy and confidentiality are not guaranteed, and potentially, you are opening yourself to privacy intrusions.

The World We Are In

It is incontrovertible that we are now amid a grandiose worldwide experiment when it comes to societal mental health. The experiment is that AI is being made available nationally and globally, which is either overtly or insidiously acting to provide mental health guidance of one kind or another. Doing so either at no cost or at a minimal cost. It is available anywhere and at any time, 24/7. We are all the guinea pigs in this wanton experiment.

The reason this is especially tough to consider is that AI has a dual-use effect. Just as AI can be detrimental to mental health, it can also be a huge bolstering force for mental health. A delicate tradeoff must be mindfully managed. Prevent or mitigate the downsides, and meanwhile make the upsides as widely and readily available as possible.

Euripides famously made this remark: “Hate is a bottomless cup; I will pour and pour.” The gist is that if you establish a relationship solely based on shared hate, the odds are that the hatred will be all-consuming, including permeating the relationship persistently. AI can potentially help you think through the consequences and guide you to avoid what might be a bitter fate.