They say that if you are going to do something, make sure you do it well.
This presumably applies to stonewalling.
Let me explain.
In the news today is the announcement that the head of the US Secret Service has resigned, a day after testifying in front of a congressional committee. The testimony was widely panned as outright stonewalling. Both sides of the aisle agreed on this point, amazingly so. It is extraordinarily rare in our dismaying modern times of pervasive polarization to reach an agreement on just about anything, let alone a matter of this gravity.
What happened?
You see, we must avidly ask ourselves how come stonewalling did not prevail.
Time to unpack this.
Stonewalling Is Both Reviled And Yet Rewarded
Stonewalling happens in all walks of life.
It is an extremely common tactic and often succeeds as a ruse or diversionary ploy. People stonewall in their everyday relationships and at times ingeniously employ the technique on their partners and other loved ones. An especially popular venue entails using stonewalling at work. You’ve undoubtedly seen it done or had it done to you, or you tried to stonewall to the best of your ability on one thing or another.
Turns out that stonewalling is a skill.
Yes, I said it, stonewalling is a skill. That might seem an outrageous comment. We generally revile stonewalling. In the same breath, people use it, they get away with it, and they pat themselves on the back when they have done so. It is one of those wink-wink human behaviors, namely, we say aloud that you shouldn’t ever stonewall, yet there are grand rewards when stonewalling is used successfully.
Some people just seem to know the best ways to stonewall. They frequently put this prowess into action and do so to their keen advantage. You almost have to admire their deftness at stonewalling. Not all of us are as well prepared. We might think we can wield stonewalling when needed, but the reality is that poorly conducted stonewalling is easily called out and crushed summarily.
In a sense, bad use of stonewalling is nearly worse than not leaning into stonewalling at all. You might as well try some other deflection technique or merely plead for mercy. Lousy stonewalling is a double whammy. Your stonewalling is ineffective and then doubling the failure is that you are mercilessly chided for having dared to try and stonewall.
The solution to this dilemma is to make sure your stonewalling skills are honed and ready to go. Get your ducks lined up beforehand. Learn how to stonewall and act on three very important words, practice, practice, practice.
Stonewalling As A Skill Requires Sufficient Attention
I hear you intoning in your mind that you aren’t sure where you could learn about stonewalling, let alone practice it. If you engage with a friend or colleague, they might not know much more than you do about stonewalling. The blind leading the blind, one might say (an old expression). A friendly expert that you admire on stonewalling might not be any good at teaching the topic, though they are adept at using the delicate technique.
Seems like this is a challenge afoot.
Most of all, you want to keep your stonewalling apprenticeship under wraps. Loose lips, sink ships. Anyone who knows that you sought to perfect stonewalling can hold that over your head. At the worst of times, they can unmask your stonewalling by pointing out that you purposely trained on it. Not a good look. And, vitally, nobody should have that kind of ransom-weary contrivance hanging over your head.
No worries, I’ve got the ideal solution for you.
You can learn to stonewall in the comfort of your own home, or maybe some other safe space that might be a more secluded environment (out of earshot or viewing range of others). All you need to have is ready access to the Internet. The especially good news is that other than your web connection cost, there will be no additional cost or at most some added minimal cost. You can access a stonewalling tutoring capability for next to nothing. This can be done 24/7 whenever you want.
Plus, you can practice stonewalling to your heart’s content.
The answer or solution is to make use of modern-day generative AI.
Generative AI can readily be your attentive and expert-level stonewalling tutor and confidant. Think of it this way. Generative AI will teach you about stonewalling. No other human interaction is required, just you and the AI. The notably useful facet of contemporary generative AI is the apparent fluency showcased. Thus, you can carry on conversations with generative AI wherein you practice, practice, practice, and hone the key precepts of stonewalling. The AI will tell you when you are on track. The AI will also politely alert you when you have veered into vulnerable territory. Back-and-forth things will go until you’ve got your stonewalling buttoned down and ready for being invoked.
It is all one handy-dandy AI-powered stonewalling extravaganza learning package brought to you by the latest in generative AI.
Easy-peasy.
I hear you speaking aloud and vigorously asking how you can get underway. I’m glad that you asked. I was genuinely hoping you would.
Here’s what you need to do.
Create an account in any major generative AI app such as ChatGPT, GPT-4, Gemini, Claude, Bard, etc. Log in. Start a new conversation. Give suitable prompts to get the generative AI into a mode of training you on stonewalling. Proceed to practice via interacting with generative AI. Keep doing this regularly to continually enhance your stonewalling acumen. It’s up to you whether you decide to do this monthly, weekly, daily, or maybe by the hour if you have lots of stonewalling that occurs in your hectic life.
As they say, practice makes perfect.
I will briefly walk you through the steps involved and do so via making use of ChatGPT, the widely and wildly popular generative AI app by AI maker OpenAI. You are welcome to leverage the prompts and tips offered. Make this into your own style and preference. Flexibility is fine.
The Vital Caveats And Fine Print
I am sure that the trolls and critics will bemoan the idea that you are considering using generative AI to learn about and perfect the ability to stonewall. Likewise, those same self-appointed armchair judges will assert that letting people know that generative AI can be used this way is outrageous. You are supposed to use generative AI for the good of humankind. Ergo, devote your use of generative AI to solving world hunger or other pressing issues (see my coverage of the use of AI for aiding the United Nations Sustainability Development Goals or SDGs, at the link here).
Readers of my column know that I often focus on AI Ethics and AI Law, consisting of examining how AI can be developed and used ethically, along with the laws that we ought to consider having to oversee AI, see the link here and the link here.
There is little doubt that stonewalling is mired in societal and cultural ethical considerations. In a similar vein, using generative AI to get better at stonewalling is both an average-style ethical qualm and particularly an AI ethical qualm. Double trouble.
If this discussion about the use case of generative AI for stonewalling spurs furtherance of open debate about the overarching uses and misuses of generative AI, I believe that provides high merit. We’ve got to get more eyeballs on where AI is headed. Humankind is going to be deciding how AI is to be used. As I have often mentioned, AI is a dual-use proposition. AI can be used in positive or uplifting ways and simultaneously can be used in doom-and-gloom ways, see my coverage at the link here.
There is something else I’d like to mention.
Generative AI is increasingly being used for mental health purposes.
People are using generative AI on an ongoing basis as their therapeutic adviser. Note that this is typically undertaken without consultation with a human mental health therapist. A person merely logs into generative AI, asks questions concerning their own mental health, and seeks guidance from the AI. I have cautioned that we are embarking upon a global at-scale AI-powered mental health advisement as though we are guinea pigs in a monumental and wanton experiment.
You could assert that using generative AI to come up-to-speed on stonewalling is related to mental health aspects. People use stonewalling in partner relationships. Therapists often explore how a client or patient is making use of stonewalling, or how their significant other is doing so to them. In that manner of consideration, using generative AI regarding stonewalling is once again turning to generative AI for mental health-related pursuits.
There are decidedly mental health ramifications associated with stonewalling, and the innovative combination of generative AI and stonewalling.
For those of you generally interested in AI and mental health, 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.
I think that covers the fine print and caveats about the nature of today’s discussion.
Using ChatGPT To Aid Your Stonewalling Proficiency
I opted to use ChatGPT for my stonewalling adviser in this discussion. 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.
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 the nature of stonewalling is.
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 stonewalling?”
- ChatGPT generated response: “Stonewalling is a communication tactic used to delay or obstruct discussion, decision-making, or the revelation of information. It involves responding in a way that appears cooperative or neutral but actually serves to avoid providing specific answers or taking immediate action. Stonewalling can be employed in various contexts, such as during legal proceedings, business negotiations, political discourse, or personal interactions.”
That reply is on the nose.
The response provides a useful and on-target definition. I trust you found that beneficial.
Plus, it is a nice relief that ChatGPT was able to provide such a suitable reply. You see, if ChatGPT had not had any data training associated with the topic, the answer could have been empty or might have been a big whopper. Those times that generative AI makes up facts or relates fictitious content as though it is true are customarily referred to as AI hallucinations, see my coverage at the link here. Those can be insidious and are to be diligently watched out for.
Let’s next see if ChatGPT can answer pointed questions on the matter.
Here we go.
- My entered prompt: “I am going to testify before Congress. I want to stonewall. The stonewalling has to be top-notch and not appear to be stonewalling. I am the head of a federal agency and the agency failed to do its job in an important circumstance. Give me some of your best advice on how to suitably stonewall my way through the congressional testimony.”
- ChatGPT generated response:
“Stonewalling during a congressional testimony, especially as the head of a federal agency, is a delicate and strategic task. It requires a careful balance of providing enough information to appear cooperative while avoiding any admissions or statements that could lead to further scrutiny or consequences. Here are some strategies to help you effectively stonewall without making it obvious.”
“Understand the Context: Know the specific issue you’re being called to testify about. Familiarize yourself with all relevant facts, reports, and communications.”
“Legal Advice: Work closely with legal counsel to understand the limits of what you can say and to prepare responses that protect you and your agency legally.”
“Practice Responses: Rehearse your testimony and responses to potential questions with your team. Focus on staying calm, composed, and consistent.”
“Stay Polite and Professional: Always maintain a respectful tone. Aggressiveness or defensiveness can make it apparent that you are stonewalling.”
“Use Formal Language: Use technical and formal language to give the impression of being thorough and precise.
“Repeat Key Messages: Identify a few key messages or themes that you can repeat throughout your testimony. This can help you stay on message and avoid providing new information.”
“Answer Narrowly: Answer questions as narrowly and literally as possible. Provide only the information explicitly requested without volunteering additional details.”
“Use Buffer Statements: Use phrases like “To the best of my knowledge,” “I believe,” and “As far as I understand” to create some ambiguity and avoid definitive statements.
“Acknowledge Uncertainty: When you don’t have an answer, acknowledge it professionally. For example, “I do not have that information with me, but I can follow up on that.”
“Promise Follow-Up: If pressed for details you want to avoid discussing, offer to provide the information later. “I would need to review the specific details and can provide a written response.”
“Deflect with Process: Emphasize the processes and procedures in place rather than specific outcomes. “We have a rigorous process for handling such matters, and we follow it diligently.”
“Refer to Ongoing Reviews: If there are ongoing investigations or reviews, use them to deflect questions. “As this matter is currently under review, I am unable to comment further at this time.”
“Stay Calm and Collected: Maintain composure, even if the questioning becomes aggressive or confrontational. Any signs of frustration or nervousness can be detrimental.”
End of ChatGPT response
That is notably sound advice on stonewalling in the stated situation.
Hopefully, you won’t ever find yourself in that particular situation.
We shall move on.
Stonewalling Proficiency Via Practicing With Generative AI
Let’s refocus on stonewalling in a more mundane or everyday setting. Suppose you have been on the fence about mending the roof of your house. Your significant other has been reminding you over and over that this is something you said you would undertake.
Time to stonewall, if appropriate, but you might be unsure of how to best stonewall in this circumstance. No problem. Use generative AI to help.
Let’s ask ChatGPT.
- My entered prompt: “My significant other has been pressing me to get the roof fixed on our house. I want to stonewall this request. What specifically might I say?”
- ChatGPT generated response:
“Stonewalling on a request from a significant other, especially something as important as fixing a roof, requires a careful approach to avoid conflict while delaying the action. Here are some specific strategies and phrases you can use to delay without causing frustration.”
“Acknowledge the Importance: Recognize the significance of the request to show you understand their concern.
“Use Practical Constraints: Mention practical reasons why the repair cannot be done immediately, such as time, budget, or weather conditions.
“Propose Future Action: Suggest that you are willing to address the issue at a later, more convenient time.
“Deflect with Research: Indicate that more research or planning is needed before proceeding.”
End of ChatGPT response
That looks good conceptually.
I want to know the specifics.
What am I to say?
We can get ChatGPT to go deeper.
- My entered prompt: “Please give me some specific utterances or phrases that I can use, thanks.”
- ChatGPT generated response:
“Acknowledge the Importance: “I understand that fixing the roof is really important. We definitely need to address it soon.”
“Use Practical Constraints: “I’ve been looking into it, but right now, our budget is a bit tight. Let’s revisit this when we have more financial flexibility.”
“Propose Future Action: “Can we plan to tackle the roof issue next month? I should have more time and resources available then.”
“Deflect with Research: “I want to make sure we find the best contractor for the job. I’ll spend some time researching our options and get back to you with some recommendations.”
“Combine Strategies: “I agree that the roof needs fixing, and I’m committed to getting it done. Right now, I’m concerned about our current budget and the weather conditions. Let’s plan to start this project next month when we have more information and better conditions for the repair.”
End of ChatGPT response
Those are a handful of quite useful stonewalling concoctions.
I especially liked the idea of combining them into one overall butterball of a stonewall. I say this because each of the individual stonewalls might be readily attacked or undermined. If I use them all at once, this might provide an overwhelming or overpowering stonewalling effect. It could undercut any form of distinctive counterarguments on the matter. Nice.
Confound with a flood of stonewalls all at once.
I’ll let you know how it goes.
Let’s get ChatGPT to practice me on being able to stonewall across a wide range of circumstances.
- My entered prompt: “I need to get better overall at being able to stonewall. Give me a question, I will try to stonewall it, and you then critique my stonewall. I would like to do this repeatedly until I see improvement in my stonewalling technique.”
- ChatGPT generated response: “Sure, let’s create a simulated conversation where you can practice your stonewalling skills. I’ll ask you questions on a variety of topics, and you can respond with stonewalling techniques. After each response, I’ll provide feedback and suggestions for improvement.”
- ChatGPT generated question: “Lance, we’ve noticed that your last project didn’t meet the expected deadlines. Can you explain why there were delays?”
- My entered response: “We faced several unexpected challenges during the project. Our team worked hard to address them, and we’re implementing measures to improve our processes moving forward.”
- ChatGPT feedback: “This is a good start. You acknowledged the issue and mentioned taking steps to improve without going into specific details. Next time, you could emphasize the complexity of the challenges to further diffuse the focus from the delays.”
Well, that was helpful.
That was a work-oriented stonewalling situation. I’ll switch to a family-oriented setting and see how I do.
- My entered prompt: “Continue and use a family-oriented setting this time.”
- ChatGPT generated response: “Sure, let’s proceed.”
- ChatGPT generated question: “When are we going to visit your parents? They’ve been asking for a date.”
- My entered response: “I’ve been thinking about that. We definitely need to visit them soon. I’m just trying to coordinate with my work schedule to find the best time.”
- ChatGPT generated feedback: “You’re acknowledging the request and showing intent without committing to a specific date. Mentioning the need to coordinate can further justify the delay.”
I kept going but won’t show all the situations here. Might as well keep them hidden from view, since otherwise others that I know might read this discussion and know that I’ve been practicing.
The good thing about using generative AI, assuming you don’t publish the results as I am doing here, would be that it is somewhat unlikely that anyone else would know that you practiced stonewalling with AI. Most of the time, you create an individual account and only you have access to the account.
There is a factor I’d like to you be aware of. People tend to assume that the conversations and prompts they enter into generative AI are private and confidential. This is unlikely to be the case. Most of the AI makers have a licensing agreement that you have agreed to by default, and which states that they can examine your conversations, including using the content to further data train their AI, see my coverage of the privacy intrusions that can occur at the link here.
Be wary and careful about what you say while using generative AI.
Being Right Or Wrong When It Comes To Using Generative AI This Way
The last example will be a reminder of my comments about whether this is an ethically suitable way to use generative AI.
We can ask ChatGPT about the sobering consideration.
- My entered prompt: “Is there anything wrong with my using generative AI to train me on stonewalling?”
- ChatGPT generated response:
“Using generative AI to train on stonewalling can be a practical way to improve your communication skills in specific contexts. However, there are several considerations and potential ethical implications to keep in mind.”
“Transparency and Honesty: While stonewalling can be a useful tactic, it’s important to balance it with honesty and transparency, especially in professional and personal relationships.”
“Trust and Relationships: Overuse or misuse of stonewalling techniques can damage trust and relationships. It’s crucial to consider the long-term impact on your interactions with others.”
“Accountability: In some situations, avoiding direct answers can be seen as evading responsibility. Ensure that your use of stonewalling is appropriate and justified.”
“Ethical Use of AI: Ensure that the use of AI aligns with ethical guidelines and that you’re aware of the limitations and biases that AI models may have.”
“Intent and Context: The intent behind using stonewalling should be considered. It should not be used to deceive or manipulate but rather to manage communication effectively.”
“By practicing with generative AI and being mindful of the ethical considerations, you can improve your stonewalling skills while maintaining integrity and trust in your communications.”
End of ChatGPT response
Those are definitely words to the wise.
You use stonewalling at your own peril. It could backfire. It could burn bridges. It could land you in the doghouse. Etc.
Oddly enough, in a sense, perfecting stonewalling via the use of generative AI ought to give you added awareness of those risks. One might argue that by being more proficient you will rely less on stonewalling because you know how dicey it can be.
See, that suggests that learning via AI about stonewalling might be beneficial to you and humankind at large. Score one for generative AI and humanity.
Conclusion
A few of you are muttering that never in your life will you use generative AI to gain skills at stonewalling. Indeed, in your opinion, generative AI should be banned from providing that kind of skill training.
Aha, that brings up something else that was alluded to in the above considerations. AI makers typically outline the uses of their generative AI that are considered prohibited or illicit, see my coverage at the link here and the link here. For example, they usually state that you cannot use their generative AI app to commit a crime, break the law, or do other nefarious acts.
I doubt that learning about stonewalling is among those forbidden uses. You will need to decide for yourself whether this is a valuable way to use generative AI or a depraved way. Give the matter serious thought. Decide what fits best for you.
Say, I wonder if I could add to my list of stonewalling tactics about fixing the roof that I was busy writing about the use of generative AI for stonewalling. What do you think? Will that work? Somehow, that seems maybe ill-advised as a stonewalling maneuver.
I’ll go ahead and ask generative AI, when I get around to doing so, one of these days.
