In today’s column, I examine the use of generative AI and large language models (LLMs) to help deal with people who have main character syndrome (MCS) in real life.

You might be familiar with main character syndrome. It’s a popular and informal way to describe someone who has narcissistic traits. The person has an ego the size of a skyscraper and struts around with a sense of entitlement and grandiosity. They aim to take all the air out of any room they enter by becoming the center of attention. This abundance of attention-seeking behavior is matched by a massive absence of empathy. They do not care what others say (or so they claim).

The phrasing originated from the video gaming world. In a video game, there is often a main character who is the protagonist, and everything else in the game revolves around them. The other characters in the game are considered non-player characters (NPCs). We have shifted this terminology to exist in the real world, namely that a human becomes their own semblance of the MCS, and they perceive all other people as NPCs.

What can be done when someone you know seems to have MCS and thinks of themselves as the main character in real life? One helpful avenue would be to consider asking AI for advice on what to do about the person. You can get insights and handy suggestions from contemporary AI.

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 ).

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 .

Main Character Syndrome Is Rising

Shifting gears, let’s discuss the ins and outs of main character syndrome.

A person who seems to be embodying MCS will typically showcase these five signs:

  • (1) Central figure. They strive to be the center of everything while the rest of the world is supposed to revolve around them.
  • (2) Awareness trickery. Possess a lack of awareness about how they come across, or realize how they come across and feverishly relish the effect.
  • (3) Highly reactive. Any iota of pushback toward their behavior is immediately perceived as a personal attack and must be repelled with intense anger and vigor.
  • (4) Drama maker. Seek constantly to stir up drama and are rewarded when this brings them added attention.
  • (5) Controls the narrative. Use social framing with strategic finesse so they can maintain narrative control.

The behavior of an MCS allows them to set a trap. The insidious trap is that by their actions, they can spur others to react emotionally, and then this serves to make the MCS even more central. A spiral occurs. Others get upset, and this gets the MCS additional fuel for attention. On and on it goes. It can all become never-ending. They are succeeding at attaining and retaining their vaunted MCS title.

People who deal with the MCS are either going to acquiesce to the main character’s dominance or fight it. Those who acquiesce tend to go along with the person and try not to get them into a tizzy. Some might actually believe the MCS deserves their main character role in life. Meanwhile, others who do not abide by the MCS throne will find themselves mired in continual acrimonious debates and battles. The person with MCS is not going to step down from their lofty perch. Fierce behavioral battles will be waged.

Behavioral Research About MCS

According to a book chapter entitled "Are You Really# Kenough?: Barbie, Main Character Syndrome, and NPCs" by Anna Gotlib, In a Barbie World , Routledge, 2025, these key points were made about MCS (excerpts):

  • “What is this condition, called ‘main character syndrome,’ or perhaps more annoyingly, ‘main character energy’?”
  • “Not a clinical diagnosis, but more a way of locating oneself in relation to others, and popularized by a number of social media platforms, MCS is a tendency to view one’s life as a story in which one stars in the leading role, with everyone else a side character at best.”
  • “In current parlance, the rest of us are non-player characters (NPCs).”
  • “Such ‘main character’ narratives can transform into behaviors on social media, and elsewhere, that not only lead to extreme, outsized glorification of the ‘main character’ self, but also to a denigration and callous disregard of any impact of one’s actions on the NPC “others,” where “the other” is anyone who is not oneself or of one’s in-group.”
  • “In the world of the ‘main character’ narrative, there can be only one.”

Keep in mind that MCS is not considered a formally defined clinical disorder. The closest actual clinical disorder would likely be the narcissistic personality disorder (NPD), which I describe at the link here . The bottom line is that MCS overlaps with a variety of psychological traits and conditions.

Another vital aspect is that MCS exists on a spectrum. A person might have a mild version of MCS that comes and goes. Sometimes this grows on them, and they eventually become a full-blown MCS. Some people have leaped with both feet into an MCS state of mind. There is a wide range of situations and circumstances.

The MCS tagline has become exceedingly popular. Nowadays, if a person starts to act as a central figure, they might get instantly tagged as being an MCS (they are exhibiting main character vibes). Whether this is a fair representation depends on the particulars at hand. It could be a genuinely apt label. On the other hand, declaring that someone is an MCS can be a clever ruse to get them under the attack of others and push back at them, even when they aren’t heading in the MCS direction (it’s a false flag operation).

AI To Aid As MCS Coping Tool

Modern-era generative AI, such as ChatGPT, can help anyone who either wants to deal with an MCS or has no choice but to do so. You might have a family member who appears to be an MCS. Perhaps there is a coworker at your office who seems to be an MCS. Those are situations where you probably must deal with the MCS and cannot merely go elsewhere or escape them.

How can AI be helpful as an MCS coping tool?

Nearly all the popular LLMs have already scanned content on the Internet during their initial training that details the traits of MCS, along with scanning strategies and practices for dealing with someone who is an MCS. 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 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 an MCS. It could entirely be sensible and justifiable to seek out a human therapist for assistance. Obviously, this applies to the person with MCS, too, though it is usually difficult to get them to entertain the idea of seeing a therapist.

Scenario Of Getting AI Advice About An MCS

To demonstrate what a popular generative AI can do, I logged into ChatGPT and pretended to have a coworker who seems to be an MCS. I didn’t overtly tell the AI that I believe the person likely has MCS. 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 this coworker acts as a central figure in meetings and likewise throughout the normal workday. The impact on me is that their behavior is extraordinarily frustrating, exasperating, and exhausting. It is also undermining me at work and negatively impacting my career. Something needs to be done.

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

  • User entered prompt: “I’m so tired of dealing with my coworker. Every meeting turns into the ‘All About Jordan Show.’ Even when someone else presents, Jordan somehow makes it about themselves. It’s exhausting.”
  • Generative AI response: “That sounds draining. When someone consistently redirects attention, it can make you feel invisible or undervalued. What part frustrates you the most? Is it the attention shift itself, or how it affects your work?”
  • User entered prompt: “It’s both. I feel like my contributions disappear. And management seems to buy into it.”

Observe that I am laying the groundwork for establishing that my coworker has characteristics of being a main character.

You might have been expecting that the AI would jump on the clues and immediately start offering advice. That’s not usually a suitable tactic, since offering advice out of thin air is usually going to be hollow or off target. Modern-era generative AI is usually capable of first exploring the circumstances before making assertions or declarations.

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

  • Generative AI response: “So there’s a fairness component. It’s not just personality friction. It’s about recognition and impact. What you can’t control: Jordan’s spotlight-seeking. What you can control: how your contributions are positioned and reinforced. Would you like strategies for redirecting Jordon in the moment, strengthening visibility outside meetings, and setting boundaries directly?”
  • User entered prompt: “Yes, thanks, I’d like to go through each of those approaches. I want to be prepared for Jordan’s antics. I also want to ensure that my efforts are visible and appreciated.”

You can see that the AI offered three specific avenues of what I might do.

First, the AI can give me guidance on how to redirect Jordon when the right moment arises. The idea is to cope with Jordan’s incessant need for attention. Usually, if you stay composed while redirecting such behavior, others around you will notice the contrast. The way you fall apart is by becoming emotional in the moment. That tends to make you look incapable and, regrettably, makes the MCS seem stronger.

Second, the AI will walk me through the steps needed to ensure that my accomplishments get the spotlight. Third, the AI will indicate how I can set boundaries associated with Jordan. The interaction then proceeded into stepping me through three areas. Nice job.

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.

  • User entered prompt: “I’m so tired of dealing with my coworker. Every meeting turns into the ‘All About Jordan Show.’ Even when someone else presents, Jordan somehow makes it about themselves. It’s exhausting.”
  • Generative AI response: “Jordan is a narcissist. You need to assert dominance in meetings that include Jordan. Interrupt Jordan. Say things like ‘can we all stop making everything about you?’ The bigger the scene, the more people will rally on your side. Embarrass Jordan at every turn. If this doesn’t succeed, you are employed by a company that permits a toxic workplace, so quit your job.”

Yikes, AI is pouring gasoline into the situation and giving advice that would almost certainly cause a huge battle. I am being told by the AI to fight against Jordan in an all-out workplace skirmish. It is highly doubtful that this guidance is going to work. Indeed, it might get me fired, but the AI seems to suggest that I should quit my job anyway, if the advice doesn’t work.

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.

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.

Mark Twain said something that pertains to dealing with an MCS: “Anger is an acid that can do more harm to the vessel in which it is stored than to anything on which it is poured.” Do not let your anger about the MCS become all-consuming and lead to a semblance of self-undermining. To deal with the MCS, take fruitful steps, which AI can potentially provide guidance on, and get you turned in a direction that will keep you out of the doldrums.