Month: May 2024

leadership dot #4293: real

Posted on by 1 Comment

I wrote yesterday (dot #4292) about writing AI prompts to make content more usable.

But if I typed in the prompt: “Write an essay about what my sister Julie and I did on our vacation to Delaware,” AI would produce believable content – even though I don’t have a sister Julie and have never been to Delaware.

There are many challenges with AI, but one of the biggest is that it has not learned how to respond with “I don’t know.” Just as those words are hard for some humans to say, AI will just fake it and provide inaccurate information or totally fabricated stories – without alerting people that what it is producing is pure fiction. It’s extremely difficult to tell what is generated by AI and what isn’t, and like the liar or con man who spins tales so convincingly, AI content is indistinguishable from what is real and what is not.

Soon, we won’t even notice the many ways it has infiltrated our lives. It’s best to become proficient and alert now to help shape the use of AI rather than being manipulated by it.

One of the leaders in this area is Dove. Building off its campaign to show a wide range of women as beautiful, Dove ran advertisements showing that an AI-generated image of “the most beautiful woman in the world” results in a stereotypical blonde, white, thin woman. AI-generated images of “the most beautiful woman according to the Dove Real Beauty campaign” feature quite different women.

Beyond advertising, Dove has created an AI playbook to help others prompt for images that are inclusive and representative of “real beauty.” It’s a comprehensive resource to help others be proactive in their interaction with AI tools.

Dove reports that by 2025 (as in next year!), 90% of online content is predicted to be generated by Artificial Intelligence! The time is now for your organization to create policies, practices, and ethical guidelines for how you will incorporate this transformational tool.

leadership dot #4292: prompting

Posted on by Leave a comment

Continuing the reflection about my Artificial Intelligence experiment (see dot #4290), I knew enough from my minimal training to have some idea of how to prompt ChatGPT to give me usable content. And the more I prompted it, the more refined my prompts became.

For example, I started with: “Write a 150-word blog post in the style of leadershipdots.com that offers advice to new supervisors about how to transition from being an individual contributor to becoming a supervisor,” but I received something that read like it was from a dissertation. So, I triggered another version with: “Re-write the above post to be more informal,” and ended up with what you read as dot #4286.

By the time I was on my third dot (#4288), my prompt read: “Write a 150-word informal blog post in the style of leadershipdots.com that offers advice to supervisors about how to deploy free resources at their disposal to increase employee engagement. Include an example and unique analogy.” In addition to machine learning, it was simultaneous human learning.

And if I didn’t like the output, I could merely type: “Try again,” and I would instantly have another version. It was as magical as I’m sure the early programmers felt when their stack of keypunch cards calculated equations faster than humans could.

Back in those days when computers were first being programmed, the common mantra was GIGO — garbage in, garbage out. The 2024 version of GIGO remains the same, only it applies to prompts — the modern-day computer code.

In the dark ages of DOS computers, I was an expert on writing commands for the mainframe system to pull specialized reports generating enrollment numbers in increasingly refined subsets. To me, writing prompts is a very similar skill. The more nuanced your query, the more usable your output. I think it’s where I came to identify the Superman “S” with specificity — the ability to be granularly specific about identifying what you want to produce is a superpower.

Writing prompts is becoming so essential for businesses to harness the power of AI that J.P. Morgan announced all incoming employees will be required to learn AI Prompt Engineering as part of their orientation, and the company is training 80,000 current employees on the skill as well. AI is permeating the banking world — and just about every other aspect of life.

Writing is just one tiny fraction of what AI can do. Maybe it’s time for you to play around on your own or to take one of the many online tutorials that abound. The sooner you learn to think in the format of how prompts are written, the sooner you will have access to the unlimited resources that prompts unlock.

One last dot on my AI experiment tomorrow…

leadership dot #4291: unique analogies

Posted on by Leave a comment

AI is strong in pattern recognition, deduction, synthesizing knowledge, and making predictions based on past actions — but it didn’t impress me with its ability to create “unique analogies” as I requested (see dot #4290).


When so prompted, AI compared a supervisor to a gardener, ship’s captain, director of a movie, coach leading a sports team, and chef. I strive to have the dots connect disparate thoughts to help create a new perspective — a new way of seeing – and none of those qualify by my definition.

However, the four AI dots I published were verbatim from what was generated. Where I think AI would be helpful is in providing an inspiration or draft that could be improved with human intervention. It’s always harder to start writing from a blank page – AI eliminates that from ever happening again. It has been drilled into me since my college journalism classes that “writing is different than editing.” AI can serve as the “writer” allowing humans to edit and improve from the base it created.


Here’s my “unique analogy” to describe AI. Writing without the aid of a computer is like sweeping with a broom. It requires 100% human effort, with no mechanical enhancements provided. Writing with a computer is like using a vacuum. It’s a tool that requires humans to exert less effort to achieve results and increase productivity. AI is like a Roomba that humans must prompt so it produces results on its own — but perhaps with negative results if not given the right instructions.

Which leads us to the critical nature of prompts…and tomorrow’s dot!

leadership dot #4290: confession

Posted on by 2 Comments

I was on vacation for the last four days, and typically when I’m away for an extended period I re-run previous dots. But this year, I tried an experiment and instead published the last four dots (#4286, #4287, #4288, #4289) generated by Chat GPT/Open AI. The photos (from Adobe) were also AI-generated. I wonder if you noticed.

I have dabbled my feet in the AI pond — I took a few LinkedIn courses, led discussions in my communication and business classes, and played around with the technology. It is staggeringly fast and on the whole, quite amazing. I thought I needed to see how it would handle writing a dot.

AI did in seconds what takes me a half hour or more. It literally took me longer to come up with a title than it did for the software to write the entire content. I prompted it to “try again” and instantly an entirely different blog post appeared. I could have spent hours being fascinated by all the variations I could conjure.

Fortunately (?), I did not like the dots that it wrote. I felt they were generic and trite and it gave me renewed motivation to continue plodding away on my own to write them manually. (Human-ly?) Had AI given me content that was indistinguishable from previous dots, I may have never written on my own again.

But, since that was not the case, I’ll continue to create dots — 100% self-made — including one tomorrow with more about my AI reflections…

P. S. Could you tell it was AI? I would love to hear your observations in the comments.

leadership dot #4289*: sacrifices

Posted on by Leave a comment

Memorial Day serves as a poignant reminder of the importance of leadership, even in the context of supervision.

Think about it: Memorial Day honors those who have bravely sacrificed for our freedoms. Similarly, supervisors often sacrifice personal time and energy to ensure the success and well-being of their teams.

Just as we remember the dedication and service of our fallen heroes, supervisors should reflect on their responsibility to guide, support, and advocate for their team members.

Memorial Day encourages us to pause and acknowledge the sacrifices made for a greater cause. Supervisors can use this time to reaffirm their commitment to serving their teams with integrity, empathy, and respect.

So as you enjoy the holiday weekend, take a moment to honor the spirit of leadership and service embodied by Memorial Day, and consider how you can apply these values to your role as a supervisor.

*Content generated by AI using the prompt: Write a 150-word informal blog post in the style of leadershipdots.com that provides a connection between Memorial Day and supervision. Try again. See dot #4290.

leadership dot #4288*: gourmet

Posted on by Leave a comment

Hey supervisors, here’s a pro tip: boost employee engagement using free resources you already have. It’s like turning everyday ingredients into a gourmet meal!

First up, tap into your team’s skills and passions. Just like a chef using fresh herbs from the garden, leverage what your team brings to the table. For instance, if someone loves graphic design, let them create posters for team events.

Next, foster a culture of recognition. It’s like adding a sprinkle of seasoning to enhance flavor. Give shoutouts in team meetings or on a shared platform to acknowledge great work. It costs nothing but goes a long way.

Lastly, encourage collaboration. Think of it as mixing different ingredients to create something delicious. Create opportunities for your team to work together on projects or brainstorm ideas. It fosters a sense of belonging and creativity.

By using these free resources wisely, you’ll create a recipe for high employee engagement that’s both effective and budget-friendly.

*Content generated by AI with the prompt: Write a 150-word informal blog post in the style of leadershipdots.com that offers advice to supervisors about how to deploy free resources at their disposal to increase employee engagement. Include an example and unique analogy. See dot #4290.

leadership dot #4287*: finding time

Posted on by Leave a comment

One of the biggest challenges of supervision is finding time to actually supervise your team. Here’s a tip: think of yourself as a gardener. Your team is like a garden, and it needs consistent care and attention to thrive.

Start by blocking out dedicated time on your calendar for check-ins and one-on-ones. Treat these meetings like regular watering sessions. For example, set aside 30 minutes every Wednesday morning for each team member. Use this time to listen, give feedback, and help with any roadblocks they’re facing, just like you’d tend to each plant’s needs.

Another trick is to delegate more. Trust your team with tasks you’d normally handle. This is like letting some plants grow on their own. For instance, if you usually handle the weekly report, assign it to a team member. It helps them grow strong and gives you extra time.

Finally, be present. When you’re with your team, really be there. Just as a gardener closely observes their garden, put away distractions and focus on your team. Making time for them isn’t just about managing your calendar; it’s about being available and approachable.

Your team, like a well-tended garden, will flourish when they know they can count on you.

*Content generated by AI using the prompt: Write a 150-word informal blog post in the style of leadershipdots.com that offers advice to supervisors about how to make time to supervise their team. Re-write the above and include an example. Re-write the above with a more unique analogy. See dot #4290.

leadership dot #4286*: new supervisors

Posted on by Leave a comment

Stepping up from being part of the team to leading it? Congrats! It’s a big change, but here’s a tip: focus on helping your team succeed instead of just getting your own tasks done. When you were doing the work, your output was what counted. Now, it’s all about your team’s performance.

Start by earning your team’s trust. Show them you care about their progress and well-being. Really listen to them and offer support when they need it. Delegate tasks to give them a chance to grow and prove themselves.

Communication is crucial. Be clear about what you expect, give helpful feedback, and be open to hearing their thoughts too. Your job now is to make sure everyone’s working together smoothly and has what they need.

Think of it this way: your main goal is to help your team develop. Their success is now a reflection of your leadership.

*Content generated by AI with the prompt: Write a 150-word blog post in the style of leadershipdots.com that offers advice to new supervisors about how to transition from being an individual contributor to becoming a supervisor. Re-write the above post to be more informal. See dot #4290.

leadership dot #4285: hose

Posted on by Leave a comment

My new air-conditioning unit (see dot #4284) has a clear hose outside the mechanism. Instead of all the parts being encased in metal, this nifty new feature easily demonstrates that the machine is doing more than pushing cold air; it is actually pulling out moisture and reducing humidity inside the house.

My previous unit may have had the same mechanism, but because I could not see it, I never considered that this was part of its function. By making the hose prominent, Lennox helped me appreciate the complexity of the machine and made it easier to spot mineral build-up.

To be sure, it’s a minor thing, but it’s usually the accumulation of little things that add up to make a difference. Think about what adjustment you can make to help something hidden become visible to others.

leadership dot #4284: division of labor

Posted on by Leave a comment

The tune-up appointment for my air-conditioner turned out to be an expensive proposition as it revealed a leak in the coil and ultimately required a new unit. But it has also been fascinating to watch the well-orchestrated process within the company as they installed it. Economist Adam Smith wrote about the division of labor, theorizing that tailoring small subsets of work to individuals would increase overall productivity. I believe my HVAC company has adopted his premise.

  • A technician came to my home to provide the initial, likely generic, tune-up appointment.
  • When it proved more problematic, he phoned an estimator who was here within minutes to provide a cost breakdown for replacement.
  • An office assistant called to schedule the appointment once I agreed to proceed. No need to waste the estimator’s (more expensive) time on (cheaper) clerical tasks.
  • Another person called to confirm the appointment.
  • A crew of three arrived on the installation day and instantly went about their separate jobs — one dismantling the outside unit and the others working in the basement.
  • The crew called a separate fabricator to make pieces the exact size needed, and then a much younger (and presumably cheaper) laborer delivered them.
  • The installers left all of the old equipment on the lawn, and the same person who delivered the new parts hauled it away, leaving the more skilled technicians to do the more advanced work without being diverted to the clean-up crew.

Such a process would not work for every company or project, but there could be elements of specialization that make sense for your organization. Assessments such as StrengthsFinder and Working Genius were created long after Smith’s time but add to your knowledge of how to pair tasks with people’s abilities instead of just their pay grade. As much as possible, structure your labor pool to capitalize on what people are best suited to do.