In today’s column, I explore the use of generative AI and large language models (LLMs) for those who need some upbeat insights about starting conversations. The use of icebreakers is a common social mechanism that can be used with people that you’ve newly met. A good icebreaker will get the conversation flowing. A lousy icebreaker could land like a dud and forever leave a foul impression on the other person.
Turns out that generative AI can be quite helpful in getting you into an icebreaker mindset and bolster your confidence for that next moment where you need to suavely begin a conversation.
Let’s talk about it.
This analysis of an innovative AI breakthrough 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). In addition, for my comprehensive analysis of how AI is being used specifically in medical and healthcare applications, such as for well-being coaching, mental health guidance, overall cognitive therapy, and mind-improving care, see the link here.
Icebreakers Are Vital
It might seem that some people are naturally able to start conversations. They appear to know just the right thing to say.
Were they born with such a knack?
Maybe, but probably more likely, is that they’ve had lots of practice. It might not be something explicitly learned and just picked up as they went along in life. This often is a gradually learned skill that grows into full adroitness (well, you can take actual classes in this too, if desired).
There is little doubt that there are good icebreakers and the otherwise to-be-avoided disagreeable icebreakers.
A problem with using a disagreeable icebreaker is that you are taking a big chance when using one. Assuming you’ve just met the other person, they might form a lasting impression of who you are and the type of person you seem to be. This anchoring can be extremely difficult to later overcome. First impressions are typically indelible.
In preparing for meeting with people, it can be a valuable payoff to come up beforehand with some ready-made icebreakers. The icebreakers need to be suitable for use. Another key facet is to deliver the icebreaker as though it is entirely off-the-cuff. Using a prepared icebreaker as though it was canned will almost be as bad as using a lousy icebreaker altogether.
Icebreakers And Practicing Via AI
So how can someone get up-to-speed on icebreakers?
Consider the human-to-human approach.
Ideally, you might want to bounce off a friend or confidant the icebreakers that you intend to use. This person or advisor could help in refining the icebreakers. They would also serve to reject ones that might seem wonderful to you but are going to be disastrous if used in actual practice.
This same advisor might also provide suggestions about icebreakers that you could consider using. The primary goal of icebreakers is to establish a connection with whomever you happen to meet, spark interest, and set a comforting foundation for engaging in a dialogue. Appearing at ease when employing an icebreaker is paramount to the process.
Here are five crucial tips about icebreakers:
- (1) Relevant icebreakers: A good icebreaker is relevant to the circumstances at hand, and is shaped based upon the context, the setting, and the shared moment. Bringing up some outlier icebreaker that doesn’t befit the occasion is not the way to proceed.
- (2) Positive-oriented icebreakers: A good icebreaker is inviting, and positive, and gets things going with an optimistic perspective. If you opt instead to be downbeat, the chances are that things will spiral further downward accordingly.
- (3) Open-ended icebreakers: A good icebreaker initiates an active dialogue. This won’t happen if you for example ask a stilted yes/no question since the person can merely recite a one-word answer. Aim for a relaxed open-ended question.
- (4) Genuine icebreakers: A good icebreaker will seemingly be from the heart and express something that shows interest in the other person. Fake icebreakers or ones that seem to be trite will rarely pay off.
- (5) Neutral icebreakers: A good icebreaker tends to be on a safe topic that won’t stir a hornet’s nest. Starting with a hefty political statement might seem clever but be prepared for a backlash if the other person doesn’t share the same viewpoint.
Preparing and practicing icebreakers with a confidant or advisor is certainly well-advised.
The issue though is that finding someone willing to spend the time to do so might be difficult. Furthermore, having to admit to that person that you are struggling with icebreakers might be a personal embarrassment. The additional issue is that you might suddenly think of an icebreaker late at night and want to immediately test it out.
A means to solve this ice-breaking advice-giving dilemma would be to consider using modern-era generative AI. The major generative AI apps are available 24×7 and can instantly assist with your icebreaking preparation needs.
Example Use Of Generative AI
I am betting that you would like to see an example of how generative AI enters this realm. I went ahead and logged into ChatGPT by OpenAI to come up with an example for you. You might find it of keen interest that ChatGPT garners a whopping 300 million weekly active users. That is a staggering amount of usage.
I briefly conducted an additional cursory analysis via other major generative AI apps, such as Anthropic Claude, Google Gemini, Microsoft Copilot, and Meta Llama, and found their answers to be about the same as that of ChatGPT. I’ll focus on ChatGPT but note that the other AI apps generated roughly similar responses.
The example involves me pretending to be going to an event and I want ChatGPT to aid me with identifying some handy icebreakers.
Here we go.
- My entered prompt: “I’m going to a group event tomorrow and I need help in starting conversations. Can you provide me with some good icebreakers?
- Generative AI response: “Of course! What kind of event is it, and who are the attendees?”
- My entered prompt: “It’s a tech meetup for software engineers and startup founders.”
- Generative AI response: “Got it. Here are some icebreaker ideas tailored for that crowd: (a) “What’s the coolest side project you’ve worked on?”, (b) “If you could instantly solve one coding challenge forever, what would it be?”, (c) “What inspired you to get into tech?”, (d) “Any exciting trends you’re keeping an eye on in the startup world?”
Note that the AI immediately expressed a sense of empathy or understanding for my expressed concerns. This might seem strange since the AI is a machine and not sentient (we don’t have sentient AI yet). Turns out that generative AI can appear to be empathetic via computational wordsmithing, see my discussion at the link here.
The AI came out quickly with several useful suggestions that are all reasonable and not somehow odd or outlandish. Another aspect to note is that the AI didn’t ridicule me or otherwise play any tomfoolery about my need for assistance. Generative AI is typically shaped to be supportive rather than combative.
Dialoguing Is Essential When Using AI
Your best bet in getting value from generative AI is to think of AI as a conversational partner.
The idea is that you are carrying on an interactive dialogue with AI. Some people do a one-and-done angle whereby they ask a question, get an answer, and do not undertake a dialogue with the AI about the matter at hand. That is a shortchanging of what AI can more fully provide. See my explanation about how to get more out of generative AI conversationally, at the link here.
To illustrate the value of engaging in a dialogue, let’s continue my discussion.
- My entered prompt: “It might be useful if I could practice using the suggested icebreakers. Can you assist?”
- Generative AI response: “Sure, let’s try the first one. You are encouraged to make each icebreaker your own in terms of tailoring it so that you are comfortable with the icebreaker.”
- My entered prompt: “Okay, let’s get started. Hi, good to meet you. As a software engineer, what is the coolest side project that you’ve worked on?”
- Generative AI response: “I’ve been experimenting with a chatbot for mental health support. It’s been a great way to learn about generative AI. How about you?”
- My entered prompt: “That’s really interesting about the chatbot that you worked on. I’d like to know more.”
- Generative AI response: “I have a suggestion for you, when you respond about wanting to know more, you might also mention a side project you’ve worked on. Doing so will put the two of you on even ground and it won’t seem like you are overly quizzing the other person.”
- My entered prompt: “Thanks, that’s a helpful tip.”
Once again, the AI was reassuring and upbeat.
A generative AI conversation can continue for as long as you wish. The other thing you can do is pause your exploration and then continue the conversation at a later date. This is handy so that you don’t have to start the conversation over from scratch. The AI will retain aspects of what you have discussed earlier in the conversation, see my explanation of how this works at the link here.
Don’t Let AI Hallucinations Mess You Up
Generative AI regrettably encounters said-to-be AI hallucinations from time to time. These are made-up confabulations that are groundless and fictitious. Bad advice can be dispensed. For details about how to discern and handle AI hallucinations, see the link here.
Let’s see what this looks like.
- My entered prompt: “I’m heading to a book event next week where a prominent author is doing book signings. I would like to have a relevant icebreaker ready to go for people that I meet there.”
- Generative AI response: “Here’s a good one. You can use an icebreaker where you ask a person what is the most favorite book that has never been written.”
- My entered prompt: “What? I don’t get it. Why would I ask about a book that has never been written? That doesn’t make sense.”
- Generative AI response: “Sorry, I made a mistake there. I meant to say that you might ask what is the most favorite book that the person has ever read. Thanks for catching that goof on my part.”
Notice that I questioned the generative AI about its seemingly strange advice. Fortunately, the AI opted to back down and admitted it was wrong. Had I not questioned the AI, there is a chance the AI might have continued with the foul advice and kept going as though it was a gem.
The key to all usage of generative AI is to stay on your toes, keep your wits about you, and always challenge and double-check anything the AI emits.
More To Keep In Mind
Suppose that you have a friend or colleague who seems to be having trouble breaking the ice with other people, and you want to aid in overcoming the difficulty. You could use generative AI to gear up for providing such assistance.
It works like this. You tell the AI in a prompt that the AI is to pretend to be a person who is having challenges starting conversations. The AI then will act that way, and you can try to guide the AI in figuring out how to be an icebreaker. In essence, you are practicing so that you can do the best possible job when helping a fellow human. For more about how to tell generative AI to carry out a pretense, known as an AI persona, see my coverage at the link here.
A word of caution before I wrap up this discussion.
This type of usage of generative AI and LLMs is essentially a form of therapy. That’s both good and bad. I have repeatedly cautioned that society is in a grand loosey-goosey experiment about the use of AI for mental health advisement. We are all guinea pigs. No one can say for sure how this is going to affect the populace on a near-term and long-term basis. The AI could at times be dispensing crummy advice and steering people in untoward directions.
It is occurring 24×7 and in pretty much any place since generative AI is available online and nearly free or at a minimal cost to anyone who wants to sign up and use it. Keep your fingers crossed as this uncontrolled experiment is getting bigger each passing day. It is all happening without any particular controls or stipulated regulations, see my analysis of what we need to do about this at the link here.
Let’s conclude with a supportive quote on the overall notion of using icebreakers and engaging in conversations with other people.
One of the most acclaimed and popular actresses of all time, Ingrid Bergman, said this about her own personality constraints: “I was the shyest human ever invented, but I had a lion inside me that wouldn’t shut up.” You can potentially make use of generative AI to find and awaken the socially adroit lion that is within you.
An additional weighty thought comes from the great poet Alfred Lord Tennyson: “The shell must break before the bird can fly.” Using generative AI can aid those who need some gentle and encouraging assistance to break out of their shell.
AI can help you soar when it comes to being adept at icebreakers.
