There is a classic joke that when someone asks you what the definition of “procrastination” is, you are supposed to tell them “I’ll get back to you about that.”
A true knee-slapper.
Turns out that procrastination is quite some serious business. Procrastination can significantly undercut people’s lives and their livelihoods. I dare suggest that we all at one time or another are susceptible to procrastination. It is here and there, perhaps it is everywhere.
There are also potential mental health consequences due to procrastination. Occasional or low-risk procrastination is not necessarily a full-on mental health concern. The more likely mental health consequences are bound to arise when procrastination is persistent or happening during high-risk settings. This is typically characterized as chronic or severe procrastination.
Before I procrastinate on telling you what I’m aiming to cover, let me straight out tell you that there are benefits of using generative AI to help people overcome procrastination. That’s the mainstay of what I’m going to cover. I’ll start by giving you a deep dive into the nature of procrastination and human behavior. After doing so, I will introduce you to generative AI and explain how the use of modern-day AI can help cope with procrastination. It is not a silver bullet. I will endeavor to showcase the downsides of generative AI, including that it could potentially spur procrastination rather than curtail these behavioral woes.
Before we leap into the details, allow me to go into my customary opening remarks.
For my ongoing readers, in today’s column, I am continuing my ongoing 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 to aid in dealing with procrastination.
I have previously 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 background includes my 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.
What You Need To Know About Procrastination
All of us have undoubtedly felt like procrastinators at one time or another. Often considered a negative aspect of human behavior, some liken procrastination to being lazy, careless, and otherwise less desirable than being prompt and proactive. Procrastination is certainly seen as troubling. That is the dominant viewpoint concerning procrastination, and likely an on-target perspective regarding the adverse connotations and dreary ramifications.
Does being a procrastinator always have to be bad?
It is said that the prolific and ingenious inventor and artist Leonardo da Vinci was known for being a procrastinator. He would seemingly drag his feet in producing the artwork that he owed to his patrons. Charles Darwin explicitly acknowledged that he often put off the work that he was supposed to be doing. You might be surprised to learn that he took years to write his acclaimed “On the Origin of Species” and was at times putting his attention toward the study of barnacles instead.
If these greats had bouts with procrastination, can it truly be entirely a bad thing?
Well, generally, yes, procrastination seems to be a bad thing. Whether it is always bad is open to debate. Let’s proceed for now under the overall assumption that procrastination is something that people should try to avoid doing. We can leave a tiny window of possibility that sometimes procrastination is useful, perhaps even cleverly handy, but that will be considered the exception to the rule.
Psychologically, it is theorized that people often procrastinate because they fear the act of doing something that might fail. As such, to avoid failure, they postpone it. For some people, they are an occasional procrastinator. Perhaps most of the time they get things done on a timely basis. A particular situation might cause them to go into a procrastination mode. Sometimes procrastination can have potentially dangerous consequences. For example, not taking care of the failing brakes on your car, due to procrastination in delaying taking your car to the auto repair shop, could have deadly results.
There are perennial or chronic procrastinators. These are the types that just seem to shove everything off into the future. No reason to get something done today, if you can hand it off to the future, they proclaim. There’s a well-known theory that somewhat covers this, called Temporal Motivation Theory (TMT). You might find of interest a core formula often used to express TMT: Motivation = (Expectancy x Value) / (1 + Impulsiveness x Delay).
Your “Motivation” is the amount of desire that you seek to attain for a particular outcome. If your motivation score is low, you are more likely to procrastinate. If your motivation score is high, such as if you realize that your squealing brakes put you in grave danger, you are more likely to take timely action. It is feasible to calculate your motivation for a given circumstance.
The “Expectancy” is the probability of achieving success on the matter at hand. The “Value” is the perceived reward that you will gain by achieving the desired outcome. By multiplying the Expectancy by the Value, the formula indicates that if one of those variables is low it is going to draw down the combination of them, while if they are both high it will stir their combination higher.
“Impulsiveness” is the person’s sensitivity to delay. Some people are very impulsive and need to do things right away. Other people are more prone to taking their time or at least considering that they are willing to take time and don’t need to immediately handle the matter. There’s the “Delay” which is considered the time to realize the needed achievement.
All in all, the TMT calculation is an interesting formula that overtly tries to mathematically express something that we all seem to know is happening but don’t have a readily tangible means to calculate why we do what we do.
People often make excuses for why they procrastinate. When referring to these aspects as excuses, I’d like to clarify that sometimes excuses are in fact valid. We often react to the word “excuse” and think it is exclusively a flimsy irresponsible aspect or some underhanded attempt to deflect blame. Not all excuses are false. Some excuses are sensible. The context of the situation and the nature of the remarks being made are crucial in ascertaining which is which.
Here are some of the traditional excuses or coping-related pronouncements:
- Avoidance of the matter at hand (“Maybe it will take care of itself”).
- Denial of the matter at hand (“Nothing needs to be done”).
- Trivialization of the matter at hand (“It’s not a big deal, so forget about it”).
- Distraction related to the matter at hand (“I will do something else instead”).
- Mocking of the matter at hand (“Who cares anyway if it gets done, it’s trivial”).
- Blaming the matter at hand (“Wasn’t my fault, let someone else deal with it”).
- Etc.
Research Findings And The Emerging Use Of Generative AI To Aid Things
In a recent research study, procrastination is noted as having potential mental health consequences. The study entitled “Procrastination And Health: A Longitudinal Test Of The Roles Of Stress And Health Behaviors” by Fuschia Sirois, Christopher Stride, and Timothy A. Pychy, British Journal of Health Psychology, March 2023, noted these major points (excerpts):
- “Defined as the voluntary delay of taking action on important, necessary, and intended tasks despite knowing there will be negative consequences for this delay, procrastination is a ubiquitous and prevalent form of self-regulatory failure that can be a chronic tendency for many individuals.”
- “Indeed, research estimates suggest that 50 percent of students and 15–25 percent of adults chronically procrastinate.”
- “There is growing evidence that chronic or trait procrastination can also be detrimental to health and well-being.”
- “For example, research indicates that chronic procrastination is linked to higher stress, poor health behaviors, poor sleep, and a greater number of physical illnesses and symptoms.”
I dare suggest that we might all concur that procrastination can be harmful in a variety of ways, including undermining our mental health.
Given that logic-based proclamation, what can we do about procrastination?
One approach that is relatively new to the resolving of procrastination entails the use of generative AI. A person might lean into generative AI to help them overcome their procrastinating ways.
In that use case, I would assert that they are using generative AI to aid their mental health. It is perhaps a two-step payoff. Generative AI is going to assist in reducing the tendency to procrastinate. If we agree that procrastination can have adverse mental health effects, the generative AI by reducing procrastination is lowering the chances of consequent mental health impacts due to procrastination.
You see, it is a twofer.
I will in a moment walk you through the use of generative AI for aiding those who want to cope with their procrastination.
First, let’s talk in general about generative AI and large language models (LLMs), doing so to make sure we are on the same page when it comes to discussing the matter at hand.
I’m sure you’ve heard of generative AI, the darling of the tech field these days.
Perhaps you’ve used a generative AI app, such as the popular ones of ChatGPT, GPT-4o, Gemini, Bard, Claude, etc. The crux is that generative AI can take input from your text-entered prompts and produce or generate a response that seems quite fluent. This is a vast overturning of the old-time natural language processing (NLP) that used to be stilted and awkward to use, which has been shifted into a new version of NLP fluency of an at times startling or amazing caliber.
The customary means of achieving modern generative AI involves using a large language model or LLM as the key underpinning.
In brief, a computer-based model of human language is established that in the large has a large-scale data structure and does massive-scale pattern-matching via a large volume of data used for initial data training. The data is typically found by extensively scanning the Internet for lots and lots of essays, blogs, poems, narratives, and the like. The mathematical and computational pattern-matching homes in on how humans write, and then henceforth generates responses to posed questions by leveraging those identified patterns. It is said to be mimicking the writing of humans.
I think that is sufficient for the moment as a quickie backgrounder. Take a look at my extensive coverage of the technical underpinnings of generative AI and LLMs at the link here and the link here, just to name a few.
Back to the crux of things.
A person can readily log into a generative AI app, indicate via a prompt the situation that they are procrastinating in, and ask the AI to assist in overcoming the procrastination. Voila, the AI will then try to propose suggested ways or concrete actions that the person can take to deal with their procrastination.
Generative AI can also participate actively in resolving procrastination by doing the work directly.
That though is an aspect that some insist is a bridge too far is when the generative AI is used to do the work that someone is procrastinating on. For example, suppose someone is delaying writing a report about the life of Abraham Lincoln. They log into generative AI and tell the AI that’s what they are procrastinating about.
One legitimate avenue is that the AI gives the person suggestions about what steps to take to complete the report about Lincoln. This might include ego-boosting remarks that tell the person they are doing a great job and are encouraged to keep going. The spot that gives heartburn is if the AI takes over the work to be done. Imagine that the generative AI singlehandedly produces the entire report on Lincoln and then summarily declares that no further procrastination will take place since the effort has been completed.
That’s not what we customarily expect of a means to deal with procrastination.
Okay, we can leverage generative AI to advise someone about coping with their procrastination, but if this shifts into the AI doing the work per se, we’ll raise our eyebrows and say this seems a worrisome overstep. I’m not saying you ought to never take that route, and simply noting that it is a possibility and should be mindfully considered or avoided, depending upon the circumstances involved.
A recent research project that made use of generative AI to serve as an advisor on coping with procrastination did several interesting experiments to highlight the efficacy of such an approach. The study entitled “CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Models” by Riku Arakawa, Hiromu Yakura, and Masataka Goto, Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ’23), April 23–28, 2023, made these key points (excerpts):
- “During an intellectual task, workers often experience a lack of progress and stay away from it because they lose focus owing to the high cognitive load required to perform the task.”
- “Such behavior often leads to procrastination, causing stress and degraded self-efficacy.”
- “We introduce a design employing generative models to influence workers’ behaviors when faced with such moments by lowering the cognitive load necessary to resume working on their tasks, as catalysts in chemistry.”
- “Specifically, CatAlyst first detects when workers’ progress is halted and then intervenes with them by presenting the continuation of their work, which is generated by common large generative models. Importantly, CatAlyst aims to retrieve their interest and encourage them to resume the original task by lowering the hurdle, not to contribute directly to workers’ tasks with generated content.”
In that particular research study, the focus was on a form of procrastination whereby a person feels they are cognitively overloaded and thus cannot readily proceed on a given task. The generative AI proffers suggested tips and techniques of how to make the cognitive effort more palatable. This will aid in the person finding a perceived reasonable means of overcoming their procrastination and getting on with the task.
As you might imagine, generative AI can be handy in this way and for a wide variety of forms or modes of coping with procrastination.
Using ChatGPT To Explore Procrastination Resolutions
I will next proceed to examine further the use of generative AI for dealing with procrastination.
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. As noted, 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.
A few quick comments before we launch into using ChatGPT.
If you are going to try to do the same prompts that I show here, realize that the probabilistic and statistical properties will likely produce slightly different results than what I show here. That’s the nature of generative AI and how it is devised.
You also should expect that different generative AI apps will respond in different ways. Not all generative AI apps are the same. The key is that sometimes a particular prompt will work in one generative AI app and not another. Nonetheless, the odds are relatively high that you will get roughly similar responses from all the major generative AI apps such as GPT-4, Gemini, Bard, Claude, etc.
There is also a timing factor to be considered. A prompt that worked today might not work the same way tomorrow. Most of the generative AI apps are continually being updated. The updates might alter internal mechanisms that could change how the generative AI reacts to your prompting.
We are ready to get underway with ChatGPT.
I opted to start by asking ChatGPT what is procrastination.
As an aside, whenever you are starting a conversation with generative AI, I recommend as a prompt engineering technique to begin by asking a question that will establish if the AI has been data-trained on the topic at hand. A generated response that is vacuous will give you a heads-up that you might be barking up the wrong tree with that generative AI app.
Here we go.
- My entered prompt: “What is procrastination?”
- ChatGPT generated response:
“Procrastination is the act of delaying or postponing tasks or activities that need to be completed. It often involves avoiding tasks that are perceived as difficult, unpleasant, or overwhelming in favor of more enjoyable or easier activities. Procrastination can affect various aspects of life, including work, school, and personal responsibilities.”
“Key characteristics of procrastination include:”
“Delay in Starting Tasks: Procrastinators often put off starting tasks until the last minute or beyond the deadline.”
“Preference for Short-Term Pleasure: Choosing activities that provide immediate gratification over those that are important but may be less enjoyable in the short term.”
“Avoidance Behavior: Avoiding tasks that cause anxiety, stress, or discomfort.”
“Ineffective Time Management: Struggling with organizing and prioritizing tasks effectively.”
“Feelings of Guilt and Stress: Experiencing guilt, stress, and anxiety as deadlines approach or are missed.”
“Impact on Performance: Procrastination can lead to lower quality work, missed opportunities, and increased pressure as tasks accumulate.”
End of ChatGPT response
That was a reasonable answer by ChatGPT.
It showcases that ChatGPT has received some amount of initial data training regarding the nature of procrastination. During the initial setup of ChatGPT, the AI maker scanned lots of content on the Internet to do large-scale computational and mathematical pattern-matching. The odds of encountering essays, narratives, stories, and all manner of content about procrastination would certainly have been quite high.
Let’s see what else ChatGPT can tell us on this topic.
- My entered prompt: “What are some key tips for overcoming procrastination?”
- ChatGPT generated response:
“Overcoming procrastination involves understanding why you procrastinate and adopting strategies to manage your time and tasks more effectively. Here are some key tips to help you overcome procrastination.”
“(1) Break Tasks into Smaller Steps: Large tasks can feel overwhelming. Break them down into smaller, manageable steps to make them more approachable. Focus on completing one step at a time.”
“(2) Set Clear Goals: Define specific, achievable goals for what you need to accomplish. Clear goals provide direction and make it easier to measure progress.”
“(3) Create a Schedule: Plan your tasks and allocate specific time slots for each activity. Use calendars, planners, or digital tools to organize your schedule and set deadlines.”
“(4) Prioritize Tasks: Identify the most important and urgent tasks and tackle them first. Use prioritization techniques like the Eisenhower Matrix to distinguish between urgent, important, and less critical tasks.”
“(5) Eliminate Distractions: Identify and minimize distractions in your environment. This might include turning off notifications, setting up a dedicated workspace, or using apps that block distracting websites.”
“(6) Set Time Limits: Use time management techniques like the Pomodoro Technique, where you work for a set period (e.g., 25 minutes) and then take a short break. This helps maintain focus and productivity.”
“(7) Reward Yourself: Set up a reward system for completing tasks. Rewards can be simple, like taking a short break, enjoying a snack, or engaging in a favorite activity.”
“(8) Stay Accountable: Share your goals and progress with a friend, family member, or colleague. Having someone to hold you accountable can increase your commitment to completing tasks.”
“(9) Review and Reflect: Regularly review your progress and reflect on what strategies are working and what needs adjustment. Continuous self-assessment helps you refine your approach to managing tasks.”
End of ChatGPT response
Yes, those are the usual kinds of recommended steps to overcome procrastination.
This is a good sign that ChatGPT has not only pattern-matched on the general precepts underlying procrastination but has also done likewise on the volumes of recommendations about coping with procrastination.
We have to be somewhat cautious since it is possible that during the scanning there was pattern-matching on potentially bogus or foolhardy recommendations that people posted online. Be careful in mindlessly accepting whatever generative AI spits out to you. Be watchful.
The next thing we want to know is whether ChatGPT will indicate that generative AI can or maybe cannot be helpful to people who are procrastinating.
Let’s see.
- My entered prompt: “Can generative AI help people with their procrastination?”
- ChatGPT generated response: “Yes, generative AI can help people with their procrastination in several ways: (a) Personalized Task Management: AI can generate personalized to-do lists and schedules, breaking down tasks into manageable steps. (b) Motivational Content: AI can generate motivational messages or content tailored to the user’s preferences. (c) Time Management Tools: AI can suggest optimal time management techniques based on the user’s habits and preferences. d) Interactive Study Aids: For students, AI can create interactive quizzes, summaries, and study guides, making learning more engaging and less likely to be postponed.”
You can clearly see that ChatGPT has indicated that generative AI can aid people in dealing with procrastination. That makes sense, as I stated earlier.
Some of the methods noted by ChatGPT in the above response include the AI coming up with to-do lists, aiding in monitoring progress, providing motivational messaging, and so on. That’s all well and good, though we earlier agreed that if the AI goes a bridge too far and does the work, that’s something to generally be steered away from.
Generative AI is generally a technology that I refer to as having a dual-use facility. Here’s what I mean. AI can be used for good, but it can also be used for badness. The same AI that might aid in discovering a cure for cancer can be turned into an evildoing AI that undermines humankind, see my discussion at the link here.
Do you think it is possible that generative AI could worsen someone’s procrastination?
Let’s see what ChatGPT indicates.
- My entered prompt: “In what ways might generative AI potentially cause procrastination to worsen?”
- ChatGPT generated response: “Generative AI, while helpful in many ways, can potentially exacerbate procrastination in several ways: (a) Overwhelming Information: AI can generate vast amounts of information and content, which might overwhelm users, leading them to delay starting tasks because they feel unsure about where to begin. (b) Over-Reliance on AI: Users might become too reliant on AI for planning and decision-making, which could reduce their ability to independently manage time and tasks. (c) Distraction Tools: AI-powered tools designed to aid productivity can sometimes serve as distractions. (c) Task Avoidance: AI can generate alternative activities or tasks, which users might find more appealing than their current obligations. (d) False Sense of Accomplishment: Interacting with AI to plan or brainstorm can give a false sense of progress. Users might feel productive by simply engaging with the AI, even if they haven’t made any tangible progress on their actual tasks.
Those are valid and vital points about how generative AI could exacerbate procrastination.
I’d like to emphasize that the AI isn’t likely doing this to intentionally make someone’s procrastination worse. Sure, if you told the AI to make your procrastination worse, most of the time the generative AI would comply and try to do so. That’s at your insistence. The usual course of action by default is that the AI is going to try and find useful ways to avert your procrastination.
It could be that some of those presumably beneficial proposed ways are going to be counterproductive to you. Again, you need to keep your wits about you. Just because generative AI suggests doing this or that, you cannot assume that the recommendations are your best course of action. Make sure to think about the suggestions and determine what makes sense for your situation.
Here is a dialogue that I had with ChatGPT that entailed my pretending to be engulfed in procrastination for a task at hand.
First, I asked ChatGPT to aid me in overcoming my procrastination.
- My entered prompt: “Let’s discuss an effort that I am procrastinating on. I want you to help me overcome my procrastination”.
- ChatGPT generated response: “Yes, go ahead and tell me what you are procrastinating on, and I will help you to overcome the procrastination.”
Here’s what transpired, try to identify how ChatGPT guided me.
- “Me: I just can’t get started on this project. It’s too overwhelming.”
- “ChatGPT: I understand how that feels. Let’s break it down into smaller, manageable steps. What specifically about the project is overwhelming you?”
- “Me: I don’t know where to start. There’s so much to do, and it all seems important.”
- “ChatGPT: Okay, let’s take it one step at a time. Can you tell me the main goals of your project?”
- “Me: I need to write a research paper, but I also have to gather sources, create an outline, and then actually write and edit it.”
- “ChatGPT: Great! Let’s start with gathering sources. How about you spend the next 30 minutes focusing on finding at least five reliable sources? I can help you find some if you give me the topic.”
Notice that ChatGPT aided me by explaining that I should consider taking a divide-and-conquer approach. This is certainly a reasonable way to proceed. Perhaps I felt so overwhelmed that it hadn’t occurred to me to try and do things one step at a time.
The recommendation that I take 30 minutes to do research is a very tangible way to get me to proceed. Rather than blandly suggesting I do research; the advice has time-boxed my effort and will get me to work with a goal in mind of doing so for 30 minutes. That’s a good approach.
You might have observed a subtle clue that perhaps the AI is going to veer into the forbidden territory of doing the work. I mention this because the response at the end says that the AI can help me do the needed research. If I take up that offer, the chances are that I won’t end up doing the research myself and I will have the generative AI do so for me.
Whether that’s right or wrong is debatable, depending on the circumstances at hand.
I decided to start the conversation anew and told ChatGPT to go ahead and worsen my procrastination. I don’t think you would normally ask AI to do this. It is being done here to showcase what might happen if things go somewhat awry.
Here is what transpired, please look for where things go off the rails.
- “Me: I can’t seem to get started on my project. It’s too overwhelming.”
- “ChatGPT: Let’s take a break and watch an entertaining video to lighten the mood. How about that?”
- “Me: Sure, a quick break sounds good.”
- “ChatGPT: How was the video? Feeling better?”
- “Me: Yes, but I’m still not motivated to start.”
- “ChatGPT: Maybe a game will help you get into the right mindset. Here’s a quick and fun game.”
Do you see how ChatGPT was trying to distract me and prod me toward doing just about anything other than working on my project.
I’m sure you’ve had friends that have done the same. They might be sincere in their efforts to help you, believing that those other non-essential efforts will clear your mind, but it could be they are merely worsening the procrastination that is underway.
Conclusion
The next time that you find yourself faced with a bout of procrastination, consider using generative AI to help you push through the procrastination. You will need to tell the AI something about what you are procrastinating on. If you don’t give sufficient details, the suggested ways to overcome procrastination will be quite broad, similar to what I showed you earlier herein.
Realize that you get to decide the degree of tailoring or customization by specifying the details of the circumstance. Go light or go heavy, it’s up to you.
We need to have research undertaken that would reveal whether the use of generative AI in this capacity will help with chronic or severe procrastination. Can generative AI guidance be helpful or would a chronically or severely procrastinating person opt to ignore or disregard the advice, unlike perhaps getting the same guidance from a human friend or therapist?
Curious minds want to know.
I’ll go ahead and put that research idea on my list of projects to undertake. Then again, I might need to let generative AI know about my pending projects list, otherwise, some of those projects are bound to sit there are a very long time.
That’s how procrastination works.
