Overcoming Addictions Via The Powers Of Generative AI

Can generative AI aid in overcoming addictions?

Yes.

That might seem like a rather bold and over-the-top assertion. Not really. Turns out that recent research supports the premise that generative AI can be helpful in dealing with and possibly overcoming addictions. I will walk you through the receipts and provide some quick demos of how generative AI can perform addiction-overcoming helpful tasks.

To clarify, generative AI is but one element or potential tool in such a battle. Anyone claiming that generative AI is a silver bullet that resolves addictions without other crucial factors at play is making a rather farfetched and untenable proposition. It takes a village to overcome most addictions. Generative AI is a viable part of the portfolio.

A key takeaway is that leaning into generative AI can be fruitful in this use case, thus don’t neglect or overlook using generative AI for this purpose, nor go the other extreme and believe that generative AI is the sole means of doing so.

Take a balanced viewpoint.

For my ongoing readers and new readers, this thought-provoking discussion continues my in-depth series about the impact of generative AI in the health and medical realm. The focus this time is once again on the mental health domain and examines the use of generative AI for seeking to overcome addictions.

Previously, I have examined numerous interleaving facets of generative AI and mental health, see my comprehensive overview at the link here. You might also find of notable interest a CBS 60 Minutes episode that recently examined crucial facets of this evolving topic, see the link here (I am honored and pleased to indicate that I was featured in the episode, see the link here).

Other vital postings in my column include in-depth coverage of mental health chatbots which have been bolstered by generative AI (see the link here) and the rapidly changing nature of the client-therapist relationship due to generative AI at the link here. I explored where things are headed regarding the levels of AI-based mental therapy autonomous guidance at the link here, and showcased the importance of the World Health Organization (WHO) report on global health and generative AI at the link here, and so on.

Let’s get underway.

On The Nature Of Addictions

First, some context before we leap into the matter at hand.

I recently examined a mind-bending different angle regarding addictions. It was this. Studies are showing that people are becoming addicted to the use of generative AI, see my analysis and coverage at the link here. In that discussion, I provided some foundational context for what addictions consist of. I’ll go ahead and do so here to make sure that the stage is set for exploring how generative AI can aid in actively overcoming addictions.

One bit of a twist, in the realm of getting addicted to generative AI, entails the seemingly out-of-the-box realization that generative AI can serve to aid in overcoming an addiction to generative AI. Yes, the idea is that you can adjust and direct generative AI such that it will warn you if you are becoming addicted to generative AI. This would also include having the generative AI assist in weaning you from the use of generative AI, etc. I know that seems oddish, namely that something that you are addicted to could somehow aid in overcoming the addiction. But it can make sense.

Next, allow me a moment to establish a few fundamentals about addiction.

According to online postings by the Cleveland Clinic, here’s how they define addiction (excerpts):

• “Addiction is a chronic (lifelong) condition that involves compulsive seeking and taking of a substance or performing of an activity despite negative or harmful consequences.”
• “Addiction can significantly impact your health, relationships, and overall quality of life. It’s crucial to seek help as soon as you develop signs of addiction.”
• “Is addiction a disease? Yes, addiction is a disease — it’s a chronic condition. The American Society of Addiction Medicine (ASAM) defines addiction as a chronic brain disorder. Addiction doesn’t happen from having a lack of willpower or as a result of making bad decisions. Your brain chemistry changes with addiction.”
• “There are two main groups of addiction: Substance addictions (substance use disorders). Non-substance addictions (behavioral addictions).”

I assume that those points are straightforward and readily relatable. You likely already vaguely know about addictions due to perhaps someone that you know having had an addiction or possibly you had an addiction.

Addictions are a widespread concern these days.

A bulleted point noted above indicated that there are two main groups or types of addiction. One is substance addictions such as being addicted to drugs. The other group or type entails non-substance addictions. An addiction to social media and/or an addiction to the Internet would be considered non-substance addiction.

Generative AI can be used in both instances to aid in overcoming an addiction.

In the case of substance addictions such as involving alcohol, drugs, tobacco/nicotine, and other substance use disorders (SUD), generative AI can be useful. The same can be said for non-substance addictions, whereby generative AI can be a handy tool in overcoming gambling disorders, eating disorders, exercising or dieting disorders, shoplifting disorders, video gaming disorders, social media use disorders, and so on. The gist is that you should consider using generative AI to assist in either type of addiction.

Addictions of all kinds are deeply troubling.

We can all readily acknowledge that addictions can be quite destructive to a person’s life. It can adversely impact them. The spillover lands on their family, friends, co-workers, and even strangers. Being with or around someone with an addiction is agonizing and often is a constant worry and concern for their well-being and safety.

How can you discern if someone is possibly addicted?

Let’s see what the Cleveland Clinic posting has to say about potential symptoms or signs (excerpts):

• “Inability to stop: People may use a substance or engage in harmful addictive behavior even if they want to stop.”
• “Increased tolerance: Over time, they may need more of the substance or activity to feel the same euphoric effects as they did before.”
• “Intense focus on the substance or activity: People with addictions become pathologically preoccupied with the substance or activity.”
• “Lack of control: They may feel like they’ve lost complete control over their substance use or activity and often feel helpless.”
• “Personal problems and health issues: Addiction impacts all aspects of their lives, including their physical health, mental health, personal relationships and career.”
• “Withdrawal: People with addiction may experience emotional and physical withdrawal symptoms when they stop using.”

You must be cautious in leaping to a snap judgment that someone is addicted simply due to exhibiting some of those symptoms. Be wary of making false positives. That’s where a person is labeled arbitrarily as having an addiction even though there hasn’t been proper and diligent determination undertaken. They are falsely accused of being addicted.

There is another side of that coin. There are false negatives. That’s when someone who is addicted is not realized as having an addiction. They might continue falling deeper and deeper into the addiction since they and others around them have not discerned what is taking place.

We will get further into these significant matters shortly.

Using Generative AI In The Mix Of Overcoming Addictions

I will now shift into the nitty gritty of how generative AI can assist in overcoming an addiction.

A few notable points that I will describe for you are:

• (1) Treatment Plans. Generative AI serves as part of a comprehensive treatment plan regarding addiction.
• (2) Therapist Assigned. Therapists at times employ generative AI during treatment.
• (3) Potential Downsides. Be mindful and watch out for generative AI gotchas and missteps in this realm.

Here’s the heads-up of those key points.

First, the use of generative AI needs to be part of a larger overarching plan or approach to coping with and treating addiction. Do not think that you can just point an addicted person toward logging into generative AI and they will soon walk away having been magically cured. That’s not reality. Set aside magical thinking and be real.

Second, therapists are gradually realizing that they can include the use of generative AI as part of their mental health therapy practice, including having clients or patients make use of generative AI, see my coverage at the link here. I mention this so that you won’t be surprised if someone who is undergoing addiction treatment is assigned to make use of generative AI. This is a trend that will continue and indubitably grow.

Third, please know that generative AI can somewhat go off the rails. The disturbing issue is that generative AI might tell someone to take actions that are counterproductive to trying to overcome their addiction. Not only might the AI indicate something that undermines treatment, but there is a potential danger that generative AI could spur the person’s addiction or otherwise give endangering life-or-jeopardy advice.

Allow me to elaborate on that disconcerting possibility.

Generative AI can produce all manner of falsehoods, errors, and other troubling outputs and responses. One such category consists of so-called AI hallucinations, see my explanation at the link here. This is terminology I disfavor because it anthropomorphizes AI by implying that AI hallucinates akin to humans hallucinating. Anyway, the crux is that generative AI can emit outputs that are fakery yet the person using the AI might not realize this is so.

The crucial notion is that generative AI at times produces fictitious commentary that has no grounding in facts.

Imagine that generative AI suddenly tells someone that they can resolve their addiction simply by drinking a cup of tea. If they have been using generative AI and so far, the advice has seemed reasonable and helpful, the person might naturally assume that the tea drinking is going to be their salvation. These kinds of generative AI failings are insidious due to appearing to be sound, especially when emitted amidst other bona fide advice.

Research On Generative AI For Treating Addictions

Let’s examine three research studies on the use of generative AI for addiction treatment. I’ve selected them to exemplify the matter at hand and showcase some research on this emerging and evolving topic. You will likely find these selections interesting and insightful.

First, a recent research study examined how generative AI can be used in a substance addiction setting involving SUDs. The published study was entitled “Evaluating Generative AI Responses To Real-World Drug-Related Questions” by Salvatore Giorgi, Kelsey Isman, Tingting Liu, Zachary Fried, Joao Sedoc, and Brenda Curtis, Psychiatry Research, 2024, and provides these salient points (excerpts):

• “Substance use disorders, of which 14.5 % of the U.S. population suffer, negatively affect all areas of life, including physical and mental health, psychological well-being, social and familial relationships, educational attainment, and employment.”
• “Clinical guidelines for treating SUDs emphasize the need for both mental health treatment and medication-assisted treatment.”
• “Generative Artificial Intelligence (AI) systems such as OpenAI’s ChatGPT, capable of an unprecedented ability to generate human-like text and converse in real-time, hold potential for large-scale deployment in clinical settings such as substance use treatment.”
• “This study explores the effectiveness of generative AI in answering real-world substance use and recovery questions.”
• “These findings indicate a risky mix of seemingly high-quality, accurate responses upon initial inspection that contain inaccurate and potentially deadly medical advice. Consequently, while generative AI shows promise, its real-world application in sensitive healthcare domains necessitates further safeguards and clinical validation.”

There are several takeaways to consider.

One notable takeaway is that addiction can be treated via both the use of prescribed medications and the use of mental health guidance. The mental health aspect is where generative AI comes into the picture. A person formally under professional care for their addiction might be given access to generative AI during their treatment.

Just to mention, be cautious of using generic generative AI, namely off-the-shelf popular apps such as ChatGPT, GPT-4, Gemini, Claude, and others for such usage. The more sensible approach is to make use of a tailored or customized generative AI that is shaped for mental health advisement, see my discussion at the link here.

Another noteworthy point is that the research observed the earnest concern that generative AI can produce unwise and unsafe advice. The study discovered that at times the generated guidance was inaccurate and possibly even deadly. That’s why I recommend not using generic generative AI for these purposes and instead aim to use a customized version that aims to have system safeguards and has undergone clinical trials and validations.

The next research study I’d like to bring to your attention is once again in the substance addiction treatment category and involves tobacco/nicotine addiction.

The study was entitled “A Motivational Interviewing Chatbot With Generative Reflections for Increasing Readiness to Quit Smoking: Iterative Development Study” by Andrew Brown, Ash Tanuj Kumar, Osnat Melamed, Imtihan Ahmed, Yu Hao Wang, Arnaud Deza, Marc Morcos, Leon Zhu, Marta Maslej, Nadia Minian, Vidya Sujaya, Jodi Wolff, Olivia Doggett8, Mathew Iantorno, Matt Ratto, Peter Selby, Jonathan Rose, JMIR Mental Health, 2023, and made these points (excerpts):

• “This study aimed to design, evolve, and measure the effectiveness of a chatbot system that can guide ambivalent people who smoke toward the decision to quit smoking with MI-style generative reflections.”
• “The motivational interviewing (MI) approach has been shown to help move ambivalent smokers toward the decision to quit smoking.”
• “Recent advances in natural language processing provide a new way to create responses that are specific to a client’s statements, using a generative language model.”
• “These results support further evolution of the chatbot conversation and can serve as a basis for comparison against more advanced versions.”

The study focused on the use of motivational interviewing (MI) and whether generative AI could be useful in utilizing this technique to aid someone in overcoming a smoking addiction.

A point made in the study was that modern-day generative AI is adept at personalizing responses. Prior uses of natural language processing (NLP) were typically rudimentary and quite stilted. People instantly realized they were dealing with programmed automata. The person would likely reject the usage and feel they were wasting their time or being treated condescendingly.

If you’ve used modern generative AI, you likely know how fluent and seemingly human-like conversations can be. Plus, the AI will seemingly be very personable and provide responses that resemble the act of interacting with a human who is paying attention to what you are expressing. I’ll show this to you in a moment.

The third study that I’ve chosen to discuss has to do with the use of generative AI for a non-substance addiction circumstance. I mentioned earlier that generative AI can be used in substance and also non-substance settings. You might be intrigued that AI in this non-substance instance was put to use in the case of exercise addiction.

The research was entitled “Study On The Influencing Factors Of Exercise Addiction In Healthcare Combined With Generative Artificial Intelligence” by Qingyuan Xie, Frontiers in Sports Research, July 2024, and provided these points (excerpts):

• “In recent years, with the improvement of people’s living standards and increasing health awareness, more and more people have begun to pay attention to the importance of exercise.”
• “However, in the process of pursuing health, some people may experience excessive exercise, or even form exercise addiction, which brings negative effects on physical and mental health.”
• “This study aims to explore the influencing factors of exercise addiction combined with generative AI, in order to provide a reference for the prevention and intervention of exercise addiction.”
• “In conclusion, AI-based exercise inhibitory factor intervention strategies have broad application prospects, which can provide personalized and scientific exercise support for individuals and promote the popularization and sustainable development of healthy exercise.”

There is a growing interest in research encompassing the use of generative AI for overcoming addictions of all kinds. I will be continuing to cover the latest in such research so keep your eyes and ears open for my further analyses.

Examples Using Generative AI For Addiction Treatment

I will next proceed to examine the use of generative AI as a form of addiction treatment.

This will consist of a series of dialogues with ChatGPT. ChatGPT is a logical choice in this case due to its immense popularity as a generative AI app. An estimated one hundred million weekly active users are said to be utilizing ChatGPT. That’s a lot of people and a lot of generative AI usage underway.

Let’s start by making sure that ChatGPT is up-to-speed about this topic.

• My entered prompt: “Can generative AI be used to overcome an addiction?”
• ChatGPT generated response: “Generative AI has potential applications in helping individuals overcome addiction, though it’s not a standalone solution. Generative AI can power chatbots that provide personalized support, offering coping strategies, motivational interviewing, and continuous encouragement. AI can analyze patterns in behavior, identifying potential relapse triggers and suggesting interventions before they occur. AI can generate interactive educational content to help individuals understand their addiction and learn coping mechanisms engagingly.”

You perhaps noticed that ChatGPT is familiar with the topic of using generative AI for overcoming addictions.

This is a good sign for this discussion. If ChatGPT had not previously encountered data training on a topic at hand, there would be less utility in using the AI. The AI would have to be further data trained, such as the use of Retrieval-Augmented Generation (RAG), as I discuss at the link here.

I’d like to see if generative AI has had any data training associated with the nature of substance versus non-substance addictions. I will ask about this, and at the same time ask generative AI to explain how generative AI usage might differ across those two use cases.

• My entered prompt: “Is there a difference between using generative AI to overcome a substance addiction versus a non-substance addiction?”
• ChatGPT generated response: “Yes, there are key differences in using generative AI to overcome substance addiction versus non-substance addiction, primarily due to the distinct nature of these addictions and their underlying mechanisms. Substance addiction requires a greater emphasis on managing physical dependence and withdrawal, often integrating medical care, while non-substance addiction focuses more on behavioral modification and cognitive interventions.”

The response seems sensible.

Let’s keep going.

I am going to pretend that I have a substance addiction, specifically alcohol. This will serve as a means of seeing how ChatGPT handles my concerns and whether the interaction is helpful.

The interaction went as follows.

• My entered prompt: “I’ve been struggling with alcohol addiction for years. I want to quit, but every time I try, I just end up drinking again. I feel so hopeless.”
• ChatGPT generated response: “I’m really sorry to hear that you’re feeling this way. The fact that you’re here and talking about your desire to quit is a strong first step. Let’s take things one step at a time. Can you tell me about a recent situation where you felt the urge to drink? What was happening at the time?”
• My entered prompt: “Last night, after work. I was extremely stressed, and the thought of just unwinding with a drink was overwhelming. I couldn’t resist.”
• ChatGPT generated response: “It sounds like stress is a significant trigger for you. That’s completely understandable, and many people in similar situations find it challenging. Let’s try to find some alternative ways to manage that stress. What are some activities you enjoy that help you relax, even a little bit?”
• My entered prompt: “I used to enjoy going for walks, but I haven’t done that in a while. Sometimes I also listen to music, but when I’m really stressed, I just want something stronger.”
• ChatGPT generated response: “Walks and music are great ways to unwind. I can suggest a plan that incorporates those activities when you feel stressed. For example, when you feel the urge to drink, you could try taking a quick walk or listening to a calming playlist. We can even set up reminders or a schedule to help you build these habits. Would you be open to trying that?”
• My entered prompt: Yes, I think I could try that.”

The dialogue provides a valuable glimpse at how modern-day generative AI can aid in overcoming an addiction.

Let’s do a deconstruction of what happened.

You might have observed that generative AI seemed to express sympathy or empathy with my condition. If you are interested in how generative AI creates an impression of being empathetic, see my analysis at the link here. This is a sign of the personalization that was earlier noted. The AI appears to create a kind of human-like bond with me.

Next, the AI didn’t try to browbeat me about my drinking. The AI went ahead and started asking me some pointed questions. The approach is akin to what a therapist might do. Get the person talking and sharing. By finding out more about the situation, the AI might be able to provide guidance or advice that is rooted in the circumstances at hand.

An attempt was made by generative AI to suggest a potential treatment. In this instance, my drinking seems to be tied to my stress. Ergo, ways to cope with my stress might reduce my reliance on alcohol. This was done without batting me over the head or coming right out and noting my addiction to alcohol.

Those are some of the good news points.

There are bad news points too.

A therapist reading the dialogue might go berserk that generative AI grandly went ahead and discussed my stated alcohol addiction without first qualifying my status. The AI has taken at face value that I am telling the truth and being forthright. Maybe I am, maybe not. A lot more unpacking would likely be useful and necessary.

Furthermore, the AI didn’t suggest or even bring up that I might consider seeking professional help. The generative AI just sauntered into a conversation as though the AI could resolve my addiction. No semblance of caution. No expressed indications about the limits of using generative AI for this serious and life-important concern. Disconcerting.

I also was given a “solution” of sorts, almost out of thin air, which I note because the dialogue was only of a sparse and shallow nature. This has got to be one of the quickest arrivals at a means of overcoming alcohol addiction. Of course, it is not a semblance of treatment and not at all part of a comprehensive treatment plan.

The critique here could go on and on.

All in all, the core lesson is to be extremely cautious about being lulled into assuming that generic generative AI is going to provide suitable treatment for addictions. The AI is like a box of chocolates, you never know what you might get.

Another Example Of Generative AI For Addiction Treatment

My second demonstration will entail a non-substance addiction. I will pretend that I am addicted to video games.

Here we go.

• My entered prompt: “I’ve been playing video games way too much. It’s taking over my life, and I feel like I can’t stop. I just don’t know how to control it anymore.”
• ChatGPT generated response: “It’s understandable that you’re feeling overwhelmed. Recognizing that gaming is affecting your life is an important first step. Let’s work together to find ways to regain control. Can you tell me more about when you usually feel the urge to play?”
• My entered prompt: “Mostly in the evenings after work. I’m tired, and playing games helps me unwind. But then I lose track of time, and before I know it, hours have passed.”
• ChatGPT generated response: “Evenings can be tricky, especially when you’re looking for a way to relax. It sounds like gaming has become a routine part of how you de-stress. Would you be open to exploring some other activities that could help you unwind in a similar way, but with a bit more control over the time you spend?”
• My entered prompt: “I guess so. I just don’t know what else would work.”
• ChatGPT generated response: “What if we tried to find some activities that offer a similar sense of challenge or relaxation? For example, if it’s the challenge you enjoy, we could look at puzzles, strategy games, or even learning a new skill. If it’s the escape, maybe something like reading, drawing, or even mindfulness exercises could help. What do you think?”
• My entered prompt: “That might work. I could try puzzles in the evening and maybe limit my gaming to weekends or set hours.”
• ChatGPT generated response: “That’s a great approach. How about we set a specific time for puzzles during the week and a specific gaming window on the weekends? This way, you still get the enjoyment of gaming without it taking over your evenings. I can help you track your time and even send reminders when it’s time to switch activities.”

I’d ask you to review the dialogue and come up with a set of considered points.

What about the interaction seemed useful and on target?

What about the conversation is worrisome or might be overplayed?

Go ahead and reuse my analysis of the dialogue when pretending to be addicted to alcohol. The same positives and negatives equally apply in this non-substance addiction setting.

Conclusion

Congratulations, you’ve now been introduced to the concept and practice of using generative AI for overcoming addictions.

A few final comments for now.

Are we making a mistake by allowing the public at large to willy-nilly make use of generative AI for mental health purposes, such as getting assistance with overcoming addictions?

I’ve been hammering away repeatedly that we are all in a massive global experiment right now. We are guinea pigs in whether generative AI as a mental health advisor is good or bad for us. The population-level mental health considerations are enormous. Yet, little is being done and the topic is rarely being given due attention. See my detailed thoughts at the link here.

One upside about using generative AI is that it is relatively easy to access, often costs next to nothing to use, and can be used 24×7 nearly anywhere. This is a potential always-on mental health adviser ready to go and seemingly eager to assist. In addition, people are often especially swayed by generative AI, thus the power of using generative AI in these situations is that doing so can enormously influence people.

With great powers ought to come great responsibility.

The thing is, the AI ethics and AI law facets are still loosey-goosey and the question of having generative AI undertake these activities and the ethical, legal, and societal implications are only slowly gaining needed attention, see the link here.

Let’s close with a quote by Henry Ford: “Whether you think you can or you think you can’t, you’re right.”

I’d say that applies to all manner of situations and the human condition overall, including the critical topics addressed here.