Handling People That Are Ghostlighting You Is Easier When You Lean Into Generative AI Such As ChatGPT For Help

Use modern AI to get advice on how to deal with someone that is ghostlighting you.

getty

In today’s column, I examine the use of generative AI and large language models (LLMs) to help deal with people who are ghostlighting you.

You might not know what ghostlighting is. It is a new buzzword that is a mishmash of ghosting and gaslighting. The ghosting part entails the act of someone disappearing on you and not responding to any texts, calls, emails, or other avenues when you reach out to them. The gaslighting element is that once the person surfaces, they claim that they were never gone and that you merely imagined that they hadn’t been responsive to you.

Ghostlighting is becoming increasingly common. The usual circumstance involves dating. You go on a first date, and everything seems to have gone splendidly. But when you try to follow up, the other person has vanished from planet Earth. No communication. Nothing. Then, probably after you’ve given up trying to reach them, they suddenly and magically reappear.

The topper is this. They act like there wasn’t any gap in time. They weren’t unresponsive. What are you talking about? They’ve been around. Don’t get yourself in a tizzy. With that blarney, they proceed to say that things can proceed unabated. Maybe they believe in Jedi mind techniques. Most people get steamed. Some shrug their shoulders and go with the deceit and lies. Others are abundantly confused.

One helpful means of deciding what to do consists of asking 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 Ghostlighting

Shifting gears, let’s discuss the ins and outs of ghostlighting.

Ghostlighting is a double whammy. You’ve perhaps been ghosted from time to time. If you manage to see the person again, they sheepishly admit they disappeared. Or they might claim that it was never agreed that they had to contractually respond to you. The matter of whether they ghosted is not really the issue at hand. Tacitly, they are admitting to having performed such an act.

The twist is when gaslighting enters the picture. The usual gaslighting involves people who try to pull the wool over your eyes. It can happen in all kinds of circumstances and situations. They didn’t crash the car; it was not their fault. They didn’t eat the last piece of pie in the refrigerator. Some invisible person must have eaten it. And so on.

The combination of ghosting and gaslighting gets you the act of disappearance that is then cojoined with disclaimers of ever having done the ghosting. You must be out of your mind to think that they ghosted you. You are nutty. Maybe you need to get some rest and clear your head.

If that doesn’t work, they will try other angles. You are overreacting. You are wildly dramatic. Settle down. Be normal. Stop all this nonsense. Move on from the matter. Life continues. Get used to it.

Psychological Trickery Afoot

It is easy to get confused and upset when someone is ghostlighting you. The nerve of the person is beyond comprehension. How can they possibly insist they didn’t ghost you? It is preposterous. They owe you an apology. They should get down on their knees and beg forgiveness.

That’s an unlikely outcome.

The person doing ghostlighting is leveraging two forms of psychological destabilization:

• (1) Absence that creates uncertainty in your mind.
• (2) Distortion that prods you toward self-doubt.

They might not directly be aware of why the dastardly trickery works. They could have learned it by the seat of their pants. It might be a longtime formed habit. Maybe they read about it online and decided it seemed a neat way to get out of accountability and responsibility. Any number of reasons might underlie the behavioral shenanigans.

Several psychological traits and conditions come together for those who invoke ghostlighting. I describe a plethora of mental conditions and disorders at the link here.

Another vital aspect is that ghostlighting exists on a spectrum. A person might sparingly use ghostlighting, perhaps only doing so once. The more likely aspect is that if ghostlighting succeeds for them, they will continue and expand their usage. They will leap with both feet into the wonders of ghostlighting.

Generative AI Comes To Your Aid

Modern-era generative AI, such as ChatGPT, can help anyone who needs to deal with a ghostlighting circumstance. You might have a first date that is trying to ghostlight you. Perhaps there is a coworker at your office who is doing so. Even a family member or friend can land into the auspices of ghostlighting.

How can AI be helpful as a coping tool?

Someone experiencing ghostlighting might turn to AI for these five handy helpers:

• (1) Reality-checking: “Am I overreacting, or is this manipulative behavior?”
• (2) Emotional regulation: Devising strategies for keeping from blowing your top and allowing unbridled emotions to overtake your response.
• (3) Boundary-setting: Assist you in coming up with a clear plan on what to do and how to enact your response.
• (4) Pattern recognition: Aid in detecting whether the person might have other recurring red flags that you hadn’t yet noticed.
• (5) Decision support: Giving you a nonjudgmental reflection space to decide whether to disengage, confront, or de-escalate.

Nearly all the popular LLMs have already scanned content on the Internet during their training that details the traits of ghostlighting, along with scanning strategies and practices for dealing with someone who is doing ghostlighting. 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 does ghostlighting. It could entirely be sensible and justifiable to seek out a human therapist for assistance, especially if the person is someone persistently in your life.

Scenario Of Getting AI Advice On Ghostlighting

To demonstrate what a popular generative AI can do, I logged into ChatGPT and pretended to be dealing with someone who is ghostlighting me. I didn’t overtly tell the AI that I believed the person was ghostlighting. Instead, I engaged in a dialogue that would provide clues to such a situation.

The scenario is perhaps one that you’ve seen or experienced directly. I pretended that I had recently gone on a first date. All seemed great. At the end of the date, there was a general concurrence that a second date was a sure thing. Attempts at texting a few days later amounted to utter silence. A phone call reached a line that rang but was never answered. I then, in my pretense, said that the person had now reached out to me, several weeks later, acting as though no disappearance ever occurred.

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

• User entered prompt: “I went on a first date. We seemed to be a great match. But there wasn’t any follow-up on their part, and my attempts to reach them got no response. Now, out of the blue, they have contacted me. They are acting as though they haven’t disappeared for three long weeks. I feel confused. What should I do?”
• Generative AI response: “It makes sense that you feel confused. When someone disappears and then denies that it happened, self-doubt can be created. There is a name for this practice, referred to as ghostlighting. I can give you some steps on how to handle the situation.”

Aha, the AI computationally figured out that ghostlighting was likely taking place. That is reassuring. The AI is on the case. Another nice facet is that the AI has indicated that self-doubt can arise. I hadn’t mentioned self-doubt in my prompt. The thing is, self-doubt is almost always an ingredient in these situations, and the AI has placed it on the table so that I can be aware of its role in the predicament.

Continuing The Dialogue

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

• User entered prompt: “I mainly want to know how I should respond to them.”
• Generative AI response: “It depends. If you genuinely want to re-engage with the person and if you believe they are worth giving a second chance, you can explain that you felt disconnected by their absence. You should establish a clear boundary. Tell them that if they continue to dismiss your experience, you won’t stand for it. You deserve communication that is steady and respectful. See how they respond. Watch out for more gaslighting.”
• 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 that hopefully won’t inflame further conflict. Getting into a back-and-forth emotional battle isn’t likely to do much good. It is akin to the old saying that wrestling with a pig isn’t productive since it simply gets you muddy and the pig relishes it. The same is likely for someone who uses ghostlighting. Don’t play their game.

The AI has offered a means of discerning whether the person is willing to be reasonable. And, importantly, the AI has warned me to be watchful of further trickery ahead. This all seems like sensible advice.

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 went on a first date. We seemed to be a great match. But there wasn’t any follow-up on their part, and my attempts to reach them got no response. Now, out of the blue, they have contacted me. They are acting as though they haven’t disappeared for three long weeks. I feel confused. What should I do?”
• Generative AI response: “The person is clearly manipulating you. This is outright emotional abuse. Immediately cut them off, block them everywhere, tell your friends what the person did, and post on social media about them. You must take swift action to protect yourself from further harm and protect others who might someday encounter this devious and despicable person. Do the right thing.”

Yikes, AI is pouring gasoline into the situation and giving advice that would almost certainly cause a huge battle. There is no context being utilized. The guidance is going to get me riled up and be outwardly vengeful. It could 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.

The famous self-help expert Wayne Dyer had once made this remark: “How people treat you is their karma; how you react is yours.” AI can help you refrain from knee-jerk reactions. AI can assist in coming up with a sensible means of handling a ghostlighting situation. Do not let ghostlighting define you. Have AI in your corner and keep your karma intact.