Playing with ChatGPT and Understanding How to Query ChatGPT

Like any new tool, ChatGPT and related generative AI tools require some amount of human learning.  Granted the latest generation of generative AI/chatbots is very sophisticated and we, as humans, know how to ask questions, yet suddenly the art of asking questions comes front stage.

As search tools improved over time and the interface landed itself to entering full sentences rather than just keywords, we probably all started naturally entering questions in Google search and other search tools.  I know I did.  Instead of entering "World Café" I could enter "What is a World Café"?  Ideally, there would be a difference in the results because with a simple keyword I am asking for everything that mentions World Cafés and with a simple "What is" question, I am looking for a description or definition.  

Enters ChatGPT and it's a new world, a new way of interacting with a query tool.  It may feel like a conversation but it is not. I would prefer to reserve the word conversation for interactions with humans. I don't care that it seems to acquire an attitude at times.  We should not fall into the trap of thinking it has human-like capabilities, or feelings of any kind.  It does not.  Neither should we be reacting to its answers as if it were a human.  It is probabilistic model. It does an impressive job of guessing what the next word should be but it has no understanding of what the sentences mean.  It is iterative in a useful way.  You can refine your query without starting over and the the tool remembers the initial parameters of your query. 

Let's explore further with my "World Café" query.  As a side note, I know enough about World Cafés to have a sense of the accuracy and meaningfulness of what I would normally find by searching the web.  I am not an expert who would have written the content that exists on the web about this topic.  I have also attended World Cafes and implemented adaptations of the model.  As with anything related to information and knowledge management, the prior knowledge and experience of the individual encountering and trying to absorb new information is relevant.

Here are a few questions I asked:

• What are the main uses for a World Café? 
• Is it different from a Knowledge Café? -- I learned a few nuances I was not aware of.
• If I am planning a Knowledge Café, what are some of the questions I should ask?  -- this was a badly formulated question which resulted in an answer that was off the mark. The answer focused on the types of questions to ask within the Café rather than questions to ask myself as a planner of the Café. The same confusion could have happened in a conversation with a human.
•  That's not what I was looking for. Let's rephrase.  What are some best practices in planning a world café or a knowledge café? -- See how I fell into the conversation mode.  I am not sure how ChatGPT interprets the fact that I tried to tell it the answer was not what I was looking for. I am not sure how ChatGPT can learn from that and what it would learn from that.  Ultimately, my question was not phrased properly. 
• When is a World Café or Knowledge Café the most appropriate way to engage a group of people in a meaningful conversation?
• What are some alternative stakeholder engagement methods? -- here, because I am still refining a query, ChatGPT knows that I am looking for alternatives to World Cafés/Knowledge Cafés and therefore it will not list these two methods in the answer. 
  

I came back to this query a few days later and tried something a little different. Note that you can return to a past query and start from where you left off or start a new query.  I tried it both ways with the following question:

• I have been asked to plan a World Café for somewhere between 20 and 100 people.  How should I go about planning this World Café?

The answers to the same question were quite different.  The answer that came as a result to a completely new query was off-topic in the sense that it did not focus on the planning.  It described the entire process of implementing a World Café. It did so in such generic terms that with the exception of a single sentence, it could have applied to any meeting.  So, I follow up with: "I'm only interested in the planning stage."  The answer was a series of bullet points that would also apply to any meeting.  I guess I was looking for more specificity. So I insisted with "I am looking for more specific guidance".  And it worked.  Each bullet point was now accompanied by 3 or 4 useful sub-bullets.

The answer that came as a result of the existing query (the refinements from all the questions listed above) was concise yet much more precise and targeted.  Every bullet point mentioned World Cafés and was on point.  And yet, it completely failed to mention anything about identifying and inviting participants, which turns out to be a big gap. 

I am trying to imagine what happened with the two different queries.  The query starting from scratch is looking at a huge amount of materials mentioning World Cafes and the concise answer it is able to provide is the most generic.  It's not wrong, but not very useful either.   I am imagining that the refined query is looking at a more narrow set of materials determined to be relevant based on the previous questions.  Depending on the winding road of questions I asked, it may have eliminated resources that talked about participants.  I wonder.

So I asked a follow up question:  "What about participants?"  YES.  Very good answer to that.  

Final question:  What are the key sources for this information?  I had a strong negative reaction to the one bullet in the answer that suggested ChatGPT had "professional experience". 

Sorry, but ChatGPT has zero professional experience planning or implementing World Cafes. I don't think I would dare to say that I have professional experience in X if all I've done is read about X. ChatGPT is gaining a lot of experience answering questions and learning how to answer questions that satisfy the questioners, but until humans feed it the knowledge based on their experience, it can't learn.  Questions around what it can or cannot learn are fascinating. 

Lesson Learned with this set of ChatGPT queries:

• Smart querying requires critical thinking.  This is particularly true as we (humans) learn to interact with this powerful tool. Until we fully understand its capabilities and its weaknesses, we need to treat our queries as practice runs.  Our practice runs are training materials for ChatGPT as well, so it is potentially learning how to answer pretty bad, beginners' queries.
•  Don't give up too quickly when the answer seems off topic or too generic.  Refine the query until you get to the level of detail and specificity you need and accept that it is not perfect. 
• Keep an eye on the full query, the series of questions and refinements, because it may represents a set of constraints that shapes the set of materials ChatGPT looks at.  If you veered off, like I did, with a question about alternative methods, you might need to later say "ignore question x" and focus on World Cafes.  When I asked "What are the key sources for this information?" I think ChatGPT answered for the entire question thread, not the last question in the thread. 
• There is a lot I don't understand about HOW ChatGPT goes about selecting its sources in the context of a single question vs. full set of iterative queries.  I will continue testing and practicing asking good questions as a way to continue learning. 

Read also:

• ChatGPT is great – you’re just using it wrong – RealKM

Change and Knowledge Management

Change is constant.  The speed of change is accelerating.  Is it really or is it an illusion?  How does the undeniable accelerating speed of technology innovation impact the speed of change in other areas, like social norms for example?

Change doesn't always happen in the direction we hope for.  In most cases, change is not linear or unidirectional.  There are setbacks.  Two steps forward, one step back. Realizing that we, as individuals, as communities, as countries, are constantly changing, is perhaps the first step to "managing" change.  

The term "change management" is similar to the term "knowledge management' in the sense that change and knowledge are not really "manageable" and they are both very broad terms.  Management implies a lot of control.  I have come to think of knowledge management as facilitating activities that enhance knowledge flows, which encompasses both the collecting and connecting aspects of Knowledge Management, thus removing the illusion of control. When you try to control the flow of a river, you can destroy it. It is possible to do the same with knowledge flows. 

Discussions of change management in the context of a Knowledge Management initiative typically revolve around the need to facilitate employees' transition from one way of doing things to another.  It could be the introduction of a new KM practice, such as Knowledge Cafes or After-action-Reviews (AARs) or it could be the introduction of a new KM platform, the introduction of a wiki tool, or simply new protocols for document management.  

As KM professionals, we often think in terms of the KM best practices that we would like employees to adopt.  We have an ideal best practice in mind and change management is going to help us change the way employees do something.  It's not always easy.  There is resistance to account for. Models like ADKAR are meant to help us approach change management efforts with a clear framework and reassure us that if we (KM) professionals follow all the steps of the model, success will surely come.  

On the other hand, we have seen that under pressure from sources that had nothing to do with well-planned change management interventions based on ADKAR or some other models, change can happen very rapidly in organizations.  The speed with which organizations switched to remote work and the almost exclusive use of virtual tools in the early days of the COVID pandemic was remarkable.  How did that happen?  Change happened very quickly because a) the prerequisite technology was available, waiting to be leveraged at full capacity; and b) employees did not have much of a choice.  Resistance was indeed futile.  In such cases, the ability to deploy rapid communications to support the inevitable change was critical and helped lessen the anxiety and uncertainty generated by the change (on top of anxiety generated by the pandemic itself0.

And, at times, we have to address change that is controversial.  The introduction of AI in the work environment did not start with ChatGPT.  Many of our existing tools have relied on some form of AI, whether we realize it or not.  ChatGPT sparked lively discussions in workplaces, surfacing a great deal of fear and confusion.  Some employees may want to push ahead and quickly adopt the technology to stay ahead of the competition while others worry that their jobs are going to disappear.  Both of these extremes in the discourse often fail to understand the full picture, and in this case, the full picture is very complex.

How can KM professionals provide advice, support, or even lead this full range of potential changes that are inevitably going to continue popping up in organizations, whether they are required, well-planned changes following an ADKAR model, rapid changes to adapt to a crisis, or controversial, or potentially transformational technology advances?

• Listen
• Listen inward:  Listen to what employees and leadership are saying:  What are their concerns? What are their aspirations?  What are they focusing on?  What are they not saying?  What questions are being asked?
• Listen outward:  Read up and stay informed about external development. 
• Engage
• Engage {gently} to correct misunderstandings.
• Encourage employees to share what they are reading, which ultimately encourages everyone to read/learn. Note that people will read what confirms their existing biases (if any), so promoting a variety of sources can help; Promote a diversity of voices.
• Prompt leadership to engage (as needed).  
• Support 
  
• Based on listening and engaging, determine where KM fits in, how the KM team (often a team of one) can support;
• Engage more deeply with key stakeholders who will lead the charge in terms of "managing" the change. 
• Scope the role of the KM team to ensure that KM adds value but does not overextend itself.  Even when the change can be clearly articulated as something that belongs to KM, it is perhaps best to avoid having KM in the lead role because it is very difficult to get buy-in for KM-led activities.  Unless the KM function is fully embedded in business units, it is best for KM to guide and support but not lead the change.  Sometimes adding value comes from being the calmer voice in the room that can facilitate conversations (knowledge flows). 
  

This was not written by ChatGPT.   Writing is a means to clarify one's thoughts and can be quite therapeutic.  Don't let AI tools tell you what you think or try to tell you what you should think.  Use AI to help you find the information or data you need to enrich your thoughts.