tag:blogger.com,1999:blog-52968312024-03-18T06:19:32.775-04:00Insight MappingApplied Insight Mapping, Knowledge Management and Organizational LearningBarbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.comBlogger436125tag:blogger.com,1999:blog-5296831.post-67629477224468868612024-03-18T06:18:00.004-04:002024-03-18T06:18:52.362-04:00KM and AI in the Workflow<p>We (KM professionals) often talk about embedding KM processes into the workflow so that KM isn't an additional burden on top of other processes. And now we see a new push to embed AI in workflows. Beyond using a GenAI interface like ChatGPT, GenAI applications can be fully integrated within the tools employees use in their daily work. Microsoft's M365 Copilot is an example of that integration. I also just saw how this integration works in Coda.<br /><br />With all the excitement over the new GenAI capabilities and bells and whistles of potential integration, let's pause to figure out how to best combine human elements of KM that leverage the best of human intelligence, human critical thinking. If we are going to dissect a process or set of processes in a workflow to integrate AI, we might as well spend some time thinking through where and how human intelligence will add value. Let's not apply AI just to save time and increase productivity. Let's revisit our workflows and integrate both AI and KM to give our brains more time to think. </p><p><b>How can we both speed up (boring, tedious tasks) and slow down to think within the same workflow?<br /></b><br />By carefully designing workflows and fostering a culture that values both AI efficiency AND human insight, organizations can create a powerful synergy. A balanced approach would ultimately lead to more innovative and thoughtful outcomes. </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-13111999603455042762024-03-16T06:52:00.001-04:002024-03-16T06:59:40.771-04:00From Montaigne's "Essais" to Knowledge Graphs<p>Pretty much everything leads to a thought related to knowledge graph these days. Here is today's train of thought:</p><p>I was considering reacquainting myself with Montaigne's essays for a number of reasons. </p><p></p><ol style="text-align: left;"><li>The style and how it relates (or not) to the blogging of today</li><li>The humanism/humanistic aspect of his writing and how it relates (or not) to today's conversations around humans and AI. </li><li>His knowledge skepticism, introspection, questioning of his own knowledge, asking "Que Sais-je?"/What do I know?</li></ol><p></p><p> <i><b>Digression Warning!</b></i></p><p>Montaigne was one of the authors I needed to study deeply in high school (French High School) to prepare for one of the end of high school exams. In fact, the French Literature exam was not at the end of the last year of high school but at the end of the second-to-last year. This involved very intense literary text analysis (for a 16-year-old) and an oral exam that required both presentation of a specific text and answering questions about the text from an examiner. You had to prepare a number of texts, come to the oral exam with a list, and the examiner would pick one and start drilling you. I remember that our teacher preparing us for this exam was very demanding and therefore prepared us very thoroughly. I bet that if by some miracle my list of prepared texts was put in front of me, I would suddenly remember a lot about each of them. Well, no great miracle needed. I found all my high school exams in the basement -- where all matters of interesting knowledge artifacts can be found. I also have some of my handwritten (cursive), in-class philosophy exam essays, but I digress even within the digression, a sure sign that this should be a separate post. </p><p>A couple of years later, I would find myself in English 101 in college in the US, totally lost trying to analyze Shakespeare and other English language literature not only because English was still challenging for me, but because the type of text analysis expected of students seemed so different. I didn't "get" the assignment and struggled in English 101. Perhaps this was an early lesson in how language, literature, and culture are so interconnected and part of what makes us so uniquely human.</p><p><i><b>End of Digression</b></i></p><p>I went down to my basement book collection and while I don't seem to have any Montaigne on hand, I did find a "Dictionnaire de Citations Francaises," 1978 edition. Luckily, quotes from long-deceased authors are reliably static, so this isn't a book that would age with time. In fact, it's probably more accurate than most web-based collection of quotes. I wanted to dig into some Montaigne quotes. </p><p><br /></p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj74x4iJVCKM_o1PL_Wz52YWHSw9_gaCQEcs98Szq6I-4e-HS8bmI3sCZzT-Errt5YgvPg0cZgw-3KogayIzv1f_jYBnO-d9yhyphenhyphenxj_L1kUCzHjeb9AX8GAbtN3igEzfAfXOeLw7rCf7-bYqSkNX9b4SK1NyWdPegybwSlPkDfyrlolN97Bp0qBftw/s4032/Dictionnaire_Citations.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="4032" data-original-width="3024" height="320" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj74x4iJVCKM_o1PL_Wz52YWHSw9_gaCQEcs98Szq6I-4e-HS8bmI3sCZzT-Errt5YgvPg0cZgw-3KogayIzv1f_jYBnO-d9yhyphenhyphenxj_L1kUCzHjeb9AX8GAbtN3igEzfAfXOeLw7rCf7-bYqSkNX9b4SK1NyWdPegybwSlPkDfyrlolN97Bp0qBftw/s320/Dictionnaire_Citations.jpg" width="240" /></a></div><p></p><p>There are multiple pages of Montaigne quotes, all from his "Essais". </p><p></p><p>It's a heavy book, like most physical dictionaries, with a narrow page. It's also a beautiful example of organized knowledge, with multiple indexes and numbered references. I can search by topic, by author, by historical period. So, immediately, I think... this needs to be turned into a knowledge graph. I want to be able to visually SEE how these 16,460 quotations are connected. Would it tell me something I can't possibly see by reading the dictionary? I would think so. Perhaps I should try on a small scale. <br /><br />That being said, focusing on individual quotes extracting from essays could really fail to convey the context and full breadth of meaning and nuances that you would get from reading the full essays. If I were asked to explain the meaning of a quote, wouldn't I want to know what was written before and after the specific quote? So, while a knowledge graph based on individual quotes might be interesting as a small scale experiment, I can already see how it would have significant flaws, unless it could be paired with access to the full text for sensemaking purposes. </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-68518420681856054722024-03-11T07:21:00.002-04:002024-03-11T07:21:44.219-04:00Two Layers of Knowledge Architecture<p>I've come across two different approaches or definitions of "knowledge architecture", and by extension, "knowledge architect". I'm not sure whether talking about them as two layers is accurate, but these two approaches are not mutually exclusive. In fact, they complement each other. <br /><b><br />#1: Strategic Framework: </b>Knowledge architecture as the framework for knowledge management, which could be the foundations for a knowledge management strategy and would include the traditional people, process, technology, and governance. This is a domain much more closely associated with organization development and learning, integrating elements to leverage both tacit and explicit knowledge. </p><p><b>#2: Organizational Schema: </b>Knowledge architecture as the rules and schemas for organizing knowledge,<b> </b>which focuses on explicit knowledge and/or data (structured and unstructured). This is a domain much more closely associated with information management and now with AI, big data, etc. It's the domain of taxonomies, ontologies, and knowledge graphs.</p><p></p><div>This is not a new story in knowledge management, but with each wave of new technology, we need to be reminded of the need for a basic knowledge management framework, a Strategic Framework (#1 Knowledge Architecture), preferably before diving into the exciting depth of the Organizational Schema (#2 Knowledge Architecture). For one, it would help organizations approach technology vendors and assess technology solutions.</div><p></p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-55235767410923046932024-03-07T06:02:00.000-05:002024-03-07T06:02:47.611-05:00Thoughts around Leveraging Credibility Perception Theory<p> This is another early morning (useful) rabbit hole which started with a post on LinkedIn about a recently published paper that "examines how individuals perceive the credibility of content originating from human authors versus content generated by large language models, like the GPT language model that powers ChatGPT, in different user interface versions." (See "<a href="https://arxiv.org/pdf/2309.02524.pdf" target="_blank">Do You Trust ChatGPT</a>" for the original paper)</p><p>I was intrigued by the theoretical foundations for this type of research rather than the results of the specific study, so I went looking up information about credibility perception theory. Obviously, I'm not going to catch up on all the relevant theoretical perspectives in a couple of hours of early morning explorations, but this initial dive generated some questions?<br /></p><p><b>First round of questions</b>: Is this issue with credibility perception specific to technology-generated or technology-mediated information and our digital world? How much of it is as old as human have applied, or failed to apply critical thinking? How much of it is based on cognitive biases and the complexities of the human brain that exist regardless of technology's impact? Conversely, how much of it is impacted by technology and especially the latest technologies that are so persuasive at times.<br /><br /><b>Second round of questions</b>: Are there variations or nuances in how credibility perception theory applies to textual information vs. visual information? I was thinking about PowerBi dashboards and other types of quantitative data visualizations that people love. How would this apply to concept maps and then more broadly, to knowledge graphs? </p><p><b>Third round of questions</b>: Based on answers to all of the above, how would the development of an ontology which would be the foundation for a knowledge graph by impacted by these insights around credibility and trust? In other words, how could we leverage insights from credibility perception theory to develop and apply good practices in the development of ontologies and associated knowledge graphs?<br /><br /></p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-80811732486751916952024-03-03T06:04:00.000-05:002024-03-03T06:04:04.066-05:00From Knowledge Cafes to Conversational Swarm Intelligence<p><span style="background-color: white; color: var(--tw-prose-bold); font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; font-weight: 600; white-space-collapse: preserve;">The Power of Conversational Swarm Intelligence: Learning from Nature</span></p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px; white-space-collapse: preserve;">Humans have always been good at writing and storing information to communicate. But, when we look at nature, we see some animals are experts at communicating and working together in real time. Birds flying together in a flock, fish moving as one in a school, and bees making decisions as a swarm show us incredible examples of teamwork. Inspired by these natural wonders, there's a new technology idea on the horizon called conversational swarm intelligence.</p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px; white-space-collapse: preserve;"><span style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: var(--tw-prose-bold); font-weight: 600;">What is Conversational Swarm Intelligence?</span></p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px; white-space-collapse: preserve;">Imagine combining the teamwork of birds, fish, and bees with our latest technology. That's what conversational swarm intelligence is about. <a href="https://amplifyingcognition.com/louis-rosenberg-conversational-swarm-intelligence-group-solution-convergence-future-advances-collective-intelligence-ac-ep33/" target="_blank">Louis Rosenberg talked about this on the Amplifying Cognition podcast</a>. It's about using technology to help people talk and make decisions together in real-time, just like some animals do in nature.</p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px; white-space-collapse: preserve;"><span style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: var(--tw-prose-bold); font-weight: 600;">How Does It Work in a Knowledge Cafe?</span></p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px; white-space-collapse: preserve;">Think about a big room where 100-200 people come together to chat in small groups of about 5-7 people. They discuss a topic, then mix up and join new groups to share what they learned. This mixing and sharing help everyone get a lot of different ideas and answers to the same question.</p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px; white-space-collapse: preserve;">Now, add an AI assistant to each group. This AI listens, records, and analyzes what everyone says and shares insights from one group to another in real time. This means everyone gets to hear and think about a wide range of ideas without having to remember and retell them. It makes the discussion richer and helps find the best answers faster.</p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px; white-space-collapse: preserve;"><b>What's next?</b></p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px; white-space-collapse: preserve;">Right now, these experiments use text chats, but imagine if this could work with spoken conversations. Someday, there might be robots sitting with us, listening, and offering insights from other groups instantly. What are the implications? How could this be used most effectively in support of human decision-making? What are some possible risks? How would this change the nature of conversations and more broadly, communications?</p><p><br /></p><p><br /></p><p><br /></p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-44417859917570065612024-02-26T05:37:00.002-05:002024-02-26T05:37:29.986-05:00Common sense and nonsense<p>While reading something about the challenges of Artificial General Intelligence (AGI), which I was trying to understand more deeply than just scanning through, I fell into a rabbit hole of concepts: common sense, critical thinking, reasoning (inductive, deductive and abductive). Then I tried to connect that to my ongoing focus on understanding knowledge graphs and the organizing principles and schemas that are meant to organize data so that machines can "understand" and even generate new insights. More and more, I am inclined to go back to an earlier interest in neuroscience, which I never pursued very deeply, but which informed some of my thinking. Understanding how we, as humans, process information, how we learn, could be critical to the development of AGI, but it's not clear to me that we should try to replicate our brains. Common sense isn't that common after all. <br /><br />I stopped there because this is way too big of a topic for a little blog post and I will only embarrass myself with nonsense. There is indeed a danger in reading broadly and then trying to write in the absence of deep knowledge and understanding. </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-90502321356471185282024-02-22T06:35:00.000-05:002024-02-22T06:35:09.964-05:00What have I done?<p> Time flies. As I contemplate my next professional life, encore career, anything but retirement, I often question myself. What have I done (really)? I managed to earn a living, which isn't nothing. I found ways to keep learning and encouraged others to learn. Those were consistent primary motivations: Earn and Learn.<br /><br />Today I asked ChatGPT what it knew about me. Sounds a little narcissistic? Well, let's just say I wanted a sense of my digital footprint and while I wasn't expecting too much, it turns out that ChatGPT easily digs out details very few people have ever read, including things I posted online just a couple of days ago. So here it is, introducing myself via ChatGPT's words, most of which cited my own words anyways coming from this Insight Mapping blog. </p><p>The following professional profile is the result of a sequence of prompts. The first two prompts were gathering background information. The third prompt was putting it all into a professional profile. The last prompt was meant to add a component (Insight Mapping), which was missing and I wanted to incorporate. </p><p><b>Barbara Fillip's Professional Profile (according to ChatGPT)</b></p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px; white-space-collapse: preserve;">Barbara Fillip is a seasoned Knowledge Management (KM) professional with over two decades of experience in facilitating individual, team, project, and organization-wide learning across international development and aerospace industries. She serves as a Senior Advisor of Knowledge Management at Chemonics International and an adjunct professor at George Mason University, where she teaches graduate courses in knowledge management and collaboration within the Schar School of Policy and Government. With a PhD in international affairs from the University of Pittsburgh Graduate School of Public and International Affairs, Fillip’s academic foundation is as robust as her professional experience.</p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px; white-space-collapse: preserve;">A hallmark of Fillip's work is her innovative use of insight mapping, a method she employs to visualize complex information systems and uncover new connections and insights within organizational knowledge. This approach underscores her expertise in not only managing but also enhancing the strategic use of knowledge through visual and analytical tools. Her dedication to integrating insight mapping into KM practices demonstrates her forward-thinking approach to addressing complex informational and organizational challenges.</p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px; white-space-collapse: preserve;">Fillip's extensive exploration into Personal Knowledge Management (PKM) has led her to develop and implement various tools and methodologies, positioning her at the forefront of the field. She advocates for the integration of knowledge management with artificial intelligence, the practical application of PKM tools like TiddlyWiki, and the strategic use of insight mapping to drive organizational learning and innovation.</p><p style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; background-color: white; border: 0px solid rgb(227, 227, 227); box-sizing: border-box; color: #0d0d0d; font-family: Söhne, ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto, Ubuntu, Cantarell, "Noto Sans", sans-serif, "Helvetica Neue", Arial, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji"; font-size: 16px; margin: 1.25em 0px 0px; white-space-collapse: preserve;">Barbara Fillip’s professional profile exemplifies a deep commitment to advancing knowledge management through innovative practices, including insight mapping, AI-enhanced tools, and PKM. Her contributions not only enhance organizational effectiveness but also offer valuable insights into the evolving landscape of knowledge management in the digital era.</p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-38551859870259924062024-02-19T05:17:00.001-05:002024-02-19T05:17:48.637-05:00AI-Augmented Insight Mapping<p><span style="background-color: white; color: #333333; font-family: inherit;">''<b>AI-Augmented Insight Mapping</b>'' is an advanced application of technology in the field of knowledge management and decision support, leveraging artificial intelligence to enhance the process of creating, visualizing, and analyzing complex relationships and insights within data. As far as I know, I am the first person to use that term. Insight mapping isn't a common term to begin with.</span></p><p><span style="font-family: inherit;">You would need:</span></p><p style="background-color: white; box-sizing: border-box; color: #333333;"><span style="font-family: inherit;">1. ''Machine Learning (ML)'': AI algorithms can analyze data, learn from patterns, and make predictions or recommendations. In insight mapping, ML can identify significant connections and trends that might not be evident through manual analysis.</span></p><p style="background-color: white; box-sizing: border-box; color: #333333;"><span style="font-family: inherit;">2. ''Natural Language Processing (NLP)'': This involves the analysis of text to extract meaningful data. NLP can be used to interpret and categorize insights from unstructured data sources, such as academic papers, news articles, and social media posts.</span></p><p style="background-color: white; box-sizing: border-box; color: #333333;"><span style="font-family: inherit;">3. ''Data Visualization'': Advanced visualization tools powered by AI can represent complex datasets in intuitive and interactive insight maps. These maps can help users explore and understand the intricacies of the data more effectively.</span></p><p style="background-color: white; box-sizing: border-box; color: #333333;">Right now I am just experimenting with and learning about Knowledge Graphs within the context of my own Personal Knowledge Management system, but the bigger picture of how all these rapidly evolving tools could be combined is quite exciting. The idea is that if I can have a deep understanding of how it works with data (especially unstructured data) that I am intimately familiar with, then I can figure out how it can be scaled to broader, organizational settings.<br /><br />----<br /><i>[Here is an example of a tenuous connection which would make me consider moving the next few lines to a different post. For the sake of the post's clarity, I should stick to one key message. For the sake of exploring broader connections and working on developing better articulations of these connections, I should keep it here. Since I am more interested in exploring connections and complexity than delivering a simple message, the next paragraph stays].</i></p><p style="background-color: white; box-sizing: border-box; color: #333333;">---- <br />This idea of exploring new concepts and tools at the individual level (within a PKM system) is connected (somehow) to another argument I have been making: Individual knowledge workers need some foundational knowledge in Personal Knowledge Management before they are asked to engage in and contribute to corporate Knowledge Management. I think the KM profession missed the opportunity to make that connection more obvious and to leverage individual incentives as a prerequisite for corporate efforts to "manage" knowledge. </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-62136863641519600992024-02-18T08:38:00.000-05:002024-02-18T08:38:08.008-05:00Cognitive Processes (Cont'd)<p>We are often not fully aware of how our experiences shape how we approach new problems. Would an increased awareness of how our experiences shapes our cognitive schema enhance our ability to problems solve?</p><p><b>Cognitive Schemas</b></p><p>Our cognitive schemas—mental frameworks helping us organize and interpret information—are intricately woven from our experiences. They play a pivotal role in how we perceive new situations, tackle problems, and make decisions. I don't spend a lot of time analyzing my own mental frameworks but once in a while, I become aware of the connection between a recent insight and a prior experience. </p><p>The trigger for this post was one such insight. I was exploring a specific aspect of the knowledge graph I am building, and I had one of those little Haha! moment when a new idea or concept emerges. These little learning moments deserve more attention than they tend to get. In the excitement of writing down the idea or exploring it further, it can be challenging to pause and ask "Where did this insight come from? What is the source?" The idea is that if I understood more about the cognitive processes that lead to an insight, I would "simply" create the conditions and environment for more insights to emerge. In fact, building a knowledge graph from my notes is an experiment to see whether and how it will facilitate "insight mapping". </p><p>Here are some ways our cognitive schema impact how we approach problem solving:</p><p><b>Pattern Recognition</b></p><p>Our brains are wired to recognize patterns based on past experiences. When faced with new problems, we subconsciously search our memory for similar situations or outcomes. This can lead to faster problem-solving but also biases our approach to what has worked or not worked in the past. I keep a digital folder for ideas that failed because you never know when they might need to be resurfaced for a second try under new and different conditions. Many are probably ideas whose time hasn't come yet and it would be a shame to dismiss them.</p><p><b>Expectations and Predictions</b></p><p>Experiences influence our expectations and predictions about future events. If past experiences have been positive, we might approach new challenges with optimism and confidence. Conversely, negative experiences could lead to apprehension or pessimism, affecting our willingness to take risks or try new solutions. By consciously shifting my perspective, I've learned to approach problems with renewed vigor, informed by the past but not shackled by it (or move on and totally unshackle myself).</p><p><b>Heuristics and Biases</b></p><p>Heuristics are mental shortcuts we use to make decisions quickly. While they can be efficient, they are also prone to biases shaped by our experiences. For example, the availability heuristic makes us overestimate the importance of information that comes to mind easily, often based on recent experiences or emotionally charged events. The advice to "sleep on it" resonates with me as a reminder of the emotional undercurrents that often drive our decisions. Giving ourselves time to detach and reflect can unearth patterns and solutions previously clouded by immediate reactions.</p><p><b>Creative Thinking and Innovation</b></p><p>Diverse experiences can enrich our cognitive schemas, making us more adaptable and creative in problem-solving. Being exposed to varied situations and learning from them can broaden our perspective, allowing us to draw on a wider range of solutions when faced with new challenges. What if we more consciously asked ourselves simple questions like, "Where and when have I encountered a similar challenge?" "How is the similar to or different from this prior experience?" I was reminded of this in the recent podcast I did with Enterprise Knowledge, during which Zach noted that I had acquired over my career, a great diversity of experiences around KM. That is very and deeply informs my approach to KM -- it may also inform why I am often frustrated with small-scale efforts that touch on a very narrow KM scope. </p><p><b>Learning and Adaptation</b></p><p>Our ability to learn from past experiences and adapt our schemas accordingly is crucial. Reflecting on what has worked or failed in the past and why can help us approach new problems more effectively, avoiding previous mistakes and being open to novel solutions. The challenge is that while learning from past experience is key, we often don't do it well and unless we are more conscientious about our approach to learning, we don't necessarily learn the right lessons, or we generalize too much and miss the point that most lessons are very contextual. When they are not context specific, they are common-sense and of limited value. </p><p>Our experiences are invaluable, yet without mindfulness, they can narrow our vision and stifle creativity. Recognizing and reflecting on the myriad ways our past influences our present can empower us to face new challenges with a balanced and open mindset, ready to draw from the past but eager to forge new paths.</p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-39135728504989926532024-02-18T08:34:00.000-05:002024-02-18T08:34:10.695-05:00It reminds me of... (cognitive processes)<p>When I get into a writing routine, even if what I am writing are insignificant notes and random blog posts, I become more aware of the cognitive processes involved. It's almost as if the brain is breathing in and out, expanding to seek out and acquire ideas, and then contracting to synthesize, clarify, and transform into a series of words. In the last couple of days, I have become particularly aware of instances when something I read or a thought related to what I am reading will remind me of something either quite distant or immediately feel connected to a very recent event or activity.</p><p>Here are two examples to illustrate:</p><p>Yesterday, as I was writing the blog post about "<a href="https://www.blogger.com/blog/post/edit/5296831/6491094035360928115">Mindset is everything</a>", I was reminded of a book I read decades ago and haven't opened since. Today, as I read a blog post online about digital hygiene, it immediately connected with the book I started reading yesterday, <i>Your Time To Thrive</i>, by Marina Khidekel. I happened to be reading the chapter on unplugging from digital gadgets. </p><p>In the first example, there is something happening in the brain that makes a connection to a deeply buried memory. The initial connection is a connection to the idea, the main argument of the book. Then I remember the book that makes that argument (I am not super confident that my recollection of the sequence of thoughts is accurate just like I know memory is fallible). I had absolutely no recollection of the author's name or what the cover of the book looked like. In fact, I did not recollect the book's title correctly. </p><p>In the second example, it is likely that having started <i>Your Time to Thrive </i>and having just completed the chapter on unplugging, my mind was attracted to a blog post on digital hygiene which I might have completely bypassed a week ago. Trying to retrace my steps, or more precisely my thoughts, it seems I scanned through the blog post precisely to see if it was related to what I had just read about unplugging. I determined that it was related but adjacent, complementary, not addressing the topic from the same angle, which was interesting in itself. </p><p>It may sound paradoxical, but in the era of rapidly advancing AI, I have a feeling (Is it a feeling or an insight?) that understanding our own human brains will become more important than ever. I don't mean that we all need to become neuroscientists but rather that critical thinking skills and learning how we learn and how we think and process information will become ever more important because of the rapid changes in our access to tools that can accelerate and augment our own cognitive capabilities. </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-64910940353609281152024-02-13T06:03:00.003-05:002024-02-13T06:03:45.951-05:00"Mindset is everything" (or not)<p><span style="font-family: times;"><span style="background-color: white; color: #333333; font-size: 15px;">I started the day with this </span><a class="tc-tiddlylink-external" href="https://www.linkedin.com/posts/futuristkeynotespeaker_gethiredaustralia-linkedintopvoices-linkedinnewsaustralia-activity-7162747916636418048-xn0N/?utm_source=share&utm_medium=member_desktop" rel="noopener noreferrer" style="box-sizing: border-box; color: #0000ee; font-size: 15px;" target="_blank">Ross Dawson post</a><span style="background-color: white; color: #333333; font-size: 15px;"> </span><a class="tc-tiddlylink tc-tiddlylink-missing" href="file:///C:/Users/barba/OneDrive/Documents/Wikis/tiddlywikilocations/Explorations%202024/Explorations_2024.html#LinkedIn" style="box-sizing: border-box; color: #5778d8; font-size: 15px; font-style: italic; text-decoration-line: none; user-select: inherit;">LinkedIn</a><span style="background-color: white; color: #333333; font-size: 15px;"> </span><span style="background-color: white; color: #333333; font-size: 15px;">post.</span></span></p><p style="background-color: white; box-sizing: border-box; color: #333333; font-size: 15px;"><span style="font-family: times;">Here is the blurb that I decided to unpack:</span></p><blockquote style="background-color: white; border-left: 5px solid rgb(187, 187, 187); box-sizing: border-box; color: #333333; font-size: 15px; margin-left: 25px; padding-left: 10px; quotes: "“" "”" "‘" "’";"><div style="box-sizing: border-box; margin-bottom: 1em; margin-top: 1em;"><span style="font-family: times;">🌱Mindset is everything.</span></div><div style="box-sizing: border-box; margin-bottom: 1em; margin-top: 1em;"><span style="font-family: times;">Constant change is a reality you need to accept and learn to love. We need to be resilient, to respond, to adapt ourselves. Those that embrace rapid shifts will see opportunities others don’t, create far greater value, help their organizations to evolve, and be in a position to savor rather than be worn down by today’s extraordinary shifts.<span style="background-color: transparent;"> </span></span></div></blockquote><p>This reminded me of a book I read in college or grad school: Underdevelopment is a State of Mind: The Latin American Case, by Lawrence E. Harrison, published in 1985. I haven't opened it in decades, but I found my copy in the basement. The argument was that Latin America was underdeveloped because of certain cultural attitudes and values prevalent in the region and that the resulting attitudes towards work, the role of women, the importance of education, time perception, and the value place on innovation and authority all play a critical role in hindering economic progress and development. </p><p>On a more personal level, it sounds like a "change your mind to change your life" slogan, an argument about how limiting beliefs are stopping you from being the best version of yourself, etc., and there is an entire literature around that. <br /><br />Let's start by taking some of the text apart:</p><p>1. Mindset is everything (?). Probably not. That is too strong of a statement. There are lots of external factors that impact an individual's ability to adapt and thrive.</p><p>2. Change fatigue is a real thing. Constant change doesn't automatically lead to better outcomes. It can lead to decreased productivity and engagement, erosion of trust, and it can contribute to a negative organizational culture, where cynicism and resistance to change become the norm. </p><p>3. Not all change is progressive. Change is not always happening in the right direction, so blindly accepting and embracing change sounds like poor advice. There are lots of historical examples of change that were initially perceived as positive and later recognized as harmful. </p><p>4. Stability and routine are crucial to psychological health and well-being. We should appreciate the benefits that some level of predictability brings to individuals and organizations. </p><p>This is where change management should be engaged, but I'm not sure change management is adapting fast enough. When constant change is applied to antiquated ways of working and traditional organizational structures, it creates a lot of pain. Individuals would find it easier to adjust their mindset if the organizational infrastructure was changing in a way that aligned with the required individual adjustments. This is going back to the fact that many external factors impact an individual's ability to rapidly shift gears and adjust to the changing winds. </p><p>And yes, we all need to build up our resilience and accept change as a constant. I don't think we should accept all change blindly. It's not resistance to change, it's critical thinking. </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-73293058819194473852024-02-12T05:41:00.000-05:002024-02-12T05:41:43.938-05:00Prompt Engineering: Human language, thought processes, and machine interpretation<p>Prompt engineering is fascinating and complex. On the one hand, it's essentially about writing a query in normal language (natural language), which is very similar to writing code in a language we all know instead of having to learn a new programming language. However, natural language is very complex. It takes each of us years to learn to understand and use it. Programming language is based on a structured logic. Natural language is more fluid, often ambiguous. <br /><br />Prompt engineering requires us to use natural language to communicate with a machine that doesn't understand natural language in the human sense. As a result, prompt engineering requires us to be much more aware of HOW we use language and HOW the machine will interpret our language. The machine interprets the prompt to guide its algorithms to the right outcome. The distinction between human cognitive processes and machine algorithms is crucial to understand and important to keep in mind as we use natural language to query machines. <br /><br />Prompt engineering requires us to examine our own cognitive processes, to analyze our mental models and to try to identify communicate our intentions, meaning, and context in such a way that the machine algorithm will be able to accurately interpret. Our assumptions, biases, and the way we frame information can significantly impact the effectiveness of prompts and the AI's responses. </p><p>In short, even though we query GenAI with natural language, which appears at first glance to be much easier than learning a programming language, a sharpened awareness of our own language is required to get the best results.</p><p>Since <a href="https://youtu.be/TYbRNQ3LxwU" target="_blank">mind-reading AI</a> is on the way, ultimately, language could disappear, but we are still far from language extinction. Until then, I will translate thoughts into words and strive to be coherent with my writing and my prompts. </p><p><br /></p><p><br /></p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-49110101414814990422024-02-10T06:58:00.004-05:002024-02-10T06:58:56.153-05:00TiddlyMap and Neo4J<p>As I continue to explore Knowledge Graphs as what I believe to be a key technology in support of Knowledge Management in the era of rapid AI advancements, I am making baby steps to learn, deploying every learning method possible. I am getting introduced to a lot of new concepts. It's easy to assign myself some readings but then I struggle to understand what I am reading because I lack some foundations. I take two steps back to get the basics right and then one step forward. </p><p>What has perhaps helped the most is connecting Knowledge Graphs to what I have learned over the years about various approaches to knowledge mapping. And then playing with tools that mimic knowledge graph technology or offer a free, simplified approach to learning. </p><p>* First, TiddlyMap has allowed me to get a grasp of nodes and relationships automatically generated based on tagging and links I create as a result of my own knowledge organization schema. Automated tagging could eventually remove the manual process of tagging but I find the cognitive processes involved in tagging to be useful to me. Learning the functionalities of the visualizations has been extremely useful to start exploring the data from different angles. Since I created all the data (my own notes), I am very familiar with the content, which makes it easier to figure out how to try to analyze it. </p><p>* Second, I opened a free account on Neo4J to try to get a sense of a real knowledge graph tool. This was a serious lightbulb moment. I will need some time to really understand the functionalities and because the sample data provided with the learning materials is not something I immediately grasp (compared to my own data in TiddlyMap), this may be a slow process. Still, what I have done with TiddlyMap in the past month or so has been excellent preparation to dive into a more robust knowledge graph tool. </p><p>TiddlyMap is a personal knowledge management tool and Neo4J is meant for much larger scale knowledge systems. They are not very comparable. Yet sometimes a tool meant for individual use can help someone grap concepts that are difficult to grasp by reading guidance, instructions, or even watching a video because the scale of implementation is very different. </p><p>I keep going back to the connections between personal knowledge management -- how individuals can proactively manage their own knowledge -- and knowledge management at the more traditional scale of the organization. Individuals who have a better grasp of how they, as individuals, handle knowledge, become more effective in supporting organizational knowledge management. </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-11196384358226143692024-02-09T04:45:00.002-05:002024-02-09T04:45:52.376-05:00AI-Enhanced Personal Knowledge Management<p> Today's train of thought comes from: "<a href="https://nesslabs.com/elephas-featured-tool" target="_blank">Augmenting Human Creativity with Ayush Chaturvedi, Co-Founder of Elephas</a>", interviewed in <a href="https://nesslabs.com/" target="_blank">Ness Labs</a>.<br /></p><p>Elephas is a personal AI writing assistant for Macbook, iPhone and iPad. I don't use Apple computers and while I have an iPhone, it's unlikely I would use it for any substantive writing. So why am I interested in learning more about this app? My interest revolves around the general concept of having a Personal Knowledge Management (PKM) tool embedded in the workflow. <br /><br />I have yet to test out Copilot in Microsoft 365 at work. That seems to be very embedded within the productivity tools within the workplace workflow. That might be great at work but the knowledge base I have accumulated and shared at work in the past five years is a fraction of the knowledge base accumulated over a 30-year career. Granted the last 15-20 years are perhaps the most relevant. <br /><br />As a side note, I started this blog 20 years ago, which seems incredibly long ago. How much of what I wrote 20 years ago is still relevant? </p><p>What I need is an AI assistant that can link to a disparate set of existing resources. As Ayush Chaturvedi points out in the interview, even the most conscientious advocate and practitioner of PKM will end up testing, adopting, rejecting, changing the suite of tools they use. The same happens in organizations. We end up with a disparate set of data sources that need to somehow be connected to the AI app and linked to each other. </p><p>I have been using TiddlyWikis for more than a decade as a PKM tool. I have accumulated many TiddlyWikis but I can relatively easily connect them. What I need now is an AI tool. Should the AI be embedded within TiddlyWiki? Should it be sitting on my desktop? Should it be cloud-based?</p><p>In Knowledge Management, we often talk about embedding KM within the workflow so that the tasks associated with managing knowledge are not separate from the workflow but rather fully integrated. Instead of having to proactively remember to save something to a knowledge base, the workflow should either automatically save to a knowledge base or at least trigger a reminder or prompt you to save (or share) to a knowledge base.</p><p>The same should be true in PKM. Advocates and practitioners of PKM are likely to be very aware of their own internalized workflows and pain points. The question then becomes, "What PKM pain points am I trying to solve with an AI assistant?" That should help inform the selection of a specific tool. Ideally, the AI-assistant tool options should not force me to switch away from my current tool set (TiddlyWiki/TiddlyMap in particular) but rather augment existing capabilities. </p><p><br /></p><p> </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-44453881002933263042024-02-08T04:30:00.003-05:002024-02-08T05:58:05.278-05:00KM Archetypes and Organizational Culture<p> ToT -- Train of thought: The way in which someone reaches a conclusion, a line of reasoning.<br /><br />* I am using the expression in a slightly different way, to reflect a much less linear process which connects one thought to another without necessarily coming to any conclusion other than A and B are now connected in some interesting new way.</p><p>* Some resources I scroll through (news, articles, etc..) are dismissed as irrelevant (at that moment) and some resources are picked up by the brain as either directly relevant to an issue that is top of mind or relevant in an adjacent way. There is a filtering that can be intentionally tweaked for improved performance. I am currently more interested in the adjacently relevant resources because of the "trains of thoughts" they generate. </p><p>* The specific train of thought today started with a presentation on KM Archetypes that is getting some recognition. <a href="https://enterprise-knowledge.com/presentation-building-for-the-km-archetypes-at-your-company/" target="_blank">Presentation: Building for the KM Archetypes at Your Company</a>, by Taylor Paschal, May 2023.</p><p>First reaction: "This has been done before". I must be getting old because the "this has been done before" reaction is becoming a recurring theme. Note that it's not "it's been tried before and it failed", but more, "this isn't new". See the work of Nick Milton and Patrick Lambe for example. <br /></p><li style="background-color: white; box-sizing: border-box; color: #333333; font-size: 15px;"><span style="font-family: inherit;"><a class="tc-tiddlylink-external" href="http://www.greenchameleon.com/thoughtpieces/archetypes.pdf" rel="noopener noreferrer" style="background-color: inherit; box-sizing: border-box; color: #0000ee;" target="_blank">Mapping the Culture of an Online Community</a>, 2005.</span></li><li style="background-color: white; box-sizing: border-box; color: #333333; font-size: 15px;"><span style="font-family: inherit;"><a class="tc-tiddlylink-external" href="https://www.nickmilton.com/2011/03/four-archetypes-in-km.html" rel="noopener noreferrer" style="background-color: inherit; box-sizing: border-box;" target="_blank">Four Archetypes in KM</a>, 2011.</span></li><li style="background-color: white; box-sizing: border-box; color: #333333; font-size: 15px;"><span style="font-family: inherit;"><a class="tc-tiddlylink-external" href="http://greenchameleon.com/thoughtpieces/pkm.pdf" rel="noopener noreferrer" style="background-color: inherit; box-sizing: border-box; color: #0000ee;" target="_blank">Personal Knowledge Management: a DIY Guide to Knowledge Management - Part 2</a>, Patrick Lambe, 2002.<br /><br />This also sounds closely related to journey mapping and personas, user-centered design, etc... <br /><br />As is often the case, my trains of thoughts don't end with a conclusion but rather with a question. The question today is: Should the KM approach align with the KM archetypes that define the existing organizational culture or should the KM approach try to change the organizational culture if such culture is part of the problem?<br /><br />Answer Part A: Leverage elements of the culture that support Knowledge Management.<br />Answer Part B: Address the more problematic elements of the culture that hinder Knowledge Management efforts once you have some buy-in and adequate support. <br /><br />Easier said than done of course. <br /><br />Thoughts for another day:</span></li><li style="background-color: white; box-sizing: border-box; color: #333333; font-size: 15px;"><span style="font-family: inherit;">Train of thought prompting is interesting too.</span></li><li style="background-color: white; box-sizing: border-box; color: #333333; font-size: 15px;"><span style="font-family: inherit;">Observing and reflecting on one's trains of thought is probably a good mindfulness practice.</span></li><p><br /></p><p><br /></p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-77831068411990011702024-02-07T05:01:00.000-05:002024-02-07T05:01:16.238-05:00Knowledge Mapping<p>Today, I am presenting the first of three lunchtime sessions on knowledge mapping. Knowledge mapping can mean many different things, so I plan on presenting a variety of maps. In the process of preparing for the sessions, which are meant to be very informal conversations, I came to recognize that when I talk about knowledge mapping others might call it information or knowledge modelling and if there is a comprehensive typology of maps, each is best suited for a specific purpose. <br /><br />Knowledge mapping also has a different meaning in Knowledge Management circles, but that's another topic. This site is called "Insight Mapping" and that's yet another niche application of the broader concept of knowledge mapping. <br /><br />Coming back to today's presentation before I digress completely, the first session will focus on mind maps. The second session (next week) will be on concept maps, which is more in line with my own mental models. The third session will take a leap into areas I am still learning, reaching into ontologies and knowledge graphs. </p><p>For the first time in many years, looking back at the various maps I have collected on this site and elsewhere, provided some useful material for reflection. <br /><br />In this context, I have also enjoyed reading <a href="http://www.meteck.org/pubcmk.html" target="_blank">Maria Keet'</a>s new book: <a href="http://www.meteck.org/modellingbook/index.html" target="_blank">The What and How of Modelling Information and Knowledge: From Mind Maps to Ontologies</a>, 2023. </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-24560799095648079652024-02-06T07:20:00.000-05:002024-02-06T07:20:49.884-05:00Synthesizing and Combining<p>RealKM is always a good source of deeper content for Knowledge Management, and it is often pointing to other relevant sources. Today, it prompted me to think about synthesizing. Something lights up in my brain just by thinking about that word. At the same time, I can't seem to easily disassociate it from combining. You synthesize and combine, or perhaps some versions of synthesizing include combining, or synthesizing across many different sources. </p><p>Today's reading: <br /><br />Gardner, H., "<a href="https://realkm.com/2024/01/30/towards-a-taxonomy-of-synthesizing/" target="_blank">Towards a taxonomy of synthesizing</a>", January 30, 2024. RealKM, originally published on the Integration and Implementation Insights blog. </p><p>This may be more critical than a simple matter of definition. I am sensing a trend in using synthesizing and summarizing as synonyms and assuming that Generative AI can adequately synthesize. I don't know that it can do what a trained human brain does to synthesize. There may be many contexts where it saves a lot of time and effort and the Generative AI summary is perfectly adequate. And there may be times when either a more sophisticated prompt will be required or a combination of human and AI would yield the best results in synthesizing. </p><p>There's much more to read around this kernel. </p><p><br /><br /></p><p><br /></p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-86820901553747497382024-02-05T05:16:00.002-05:002024-02-05T05:16:22.008-05:00GPTs that ask questions rather than provide immediate answers<p>Something that resonated with me on LinkedIn today:</p><p>"<a href="https://www.linkedin.com/pulse/genai-must-ask-questions-just-give-answers-gianni-giacomelli-yrhaf%3FtrackingId=cSjMHls0TeGksvh%252FuAzNnw%253D%253D/?trackingId=cSjMHls0TeGksvh%2FuAzNnw%3D%3D" target="_blank">GenAI must ask questions, not just give answers</a>," by Gianni Giacomelli. There are times when we can use GenAI to get an answer to a question, and then always question that answer, and there are times when we should use GenAI to prompt our own thinking by asking us questions and questioning our own assumptions. <br /><br />To push this human prompting further, meaning here that the humans are bring prompted to think by being asked questions, we can use multiple GenAI tools since they all behave slightly differently based on their respective designs. </p><p>And a reminder: "As a not-so-small aside these considerations should also remind us that it is also dangerous to put humans into a position of dependency on the AI machine, as this might lead to atrophying core cognitive traits -- such as symbolic and critical, logical thinking -- that people have. Designing for active interaction between humans and machines is crucial to maintaining the vitality of human intelligence," writes Gianni Giacomelli. </p><p>This all resonated with me because I created a GPT a few days ago that does nothing but ask me questions about a specific topic of interest. Essentially, it is always phrasing things as a question for me to ponder. "Have you considered Y?" "What are your personal values around X? "Why would you do Z?" It can be designed to be a contrarian assistant that continuously probes your own thinking patterns, questions your assumptions. Useful or annoying? I say "Useful". </p><p> </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-15102159247655051072024-02-04T05:22:00.005-05:002024-02-04T05:47:21.829-05:00Personal Knowledge Management (Revisited)<p> </p><ul style="background-color: white; box-sizing: border-box; color: #333333; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 15px;"><li style="box-sizing: border-box;"><span style="box-sizing: border-box; font-weight: bolder;">Open-source Personal KM Apps</span>: For those seeking personal KM solutions, Medevel.com lists 25 open-source apps suitable for Windows, Linux, and macOS. Tools like Obsidian, Zim Wiki, and <a class="tc-tiddlylink tc-tiddlylink-missing" href="file:///C:/Users/barba/OneDrive/Documents/Wikis/tiddlywikilocations/Explorations%202024/Explorations_2024.html#TiddlyWiki" style="box-sizing: border-box; color: #5778d8; font-style: italic; text-decoration-line: none; user-select: inherit;">TiddlyWiki</a> are praised for their flexibility, customization, and ability to manage complex information efficiently. (<a class="tc-tiddlylink-external" href="https://medevel.com/25-personal-knowledge-management/" rel="noopener noreferrer" style="background-color: inherit; box-sizing: border-box; color: #0000ee;" target="_blank">Source</a>). Feb. 3, 2024. <br /><br />The text above is a blurb generated by a GPT I've set up to scan for relevant information about Knowledge Management. The results are not perfect. For example, even though the prompt specifies to look for information from the last 30 days, it did manage to give me one item from 2022. I am not looking for perfection. It provides thinking and writing prompt ideas and keeps me up to speed.<br /><br />I was glad to see TiddlyWiki mentioned. This year, I am returning to <a href="https://tiddlymap.org/" target="_blank">TiddlyMap</a> and having a lot of fun with it. I am treating it as a learning experiment, trying to build my own mini Knowledge Graph based on my own data and my own simple ontology. TiddlyMap is a plugin for TiddlyWiki that includes a mapping functionality. It's only February 4th, I started adding content to the wiki about a month ago, and already, it's a challenge to remember everything I've added. Yet, with a clear organizing scheme and consistent tagging, I can visually look a subsets of content pieces and navigate based on my own mental framework. For example, one of the key components of my learning journey this year is Knowledge Graphs. Here is what the map around Knowledge Graphs looks like as of today. <div class="separator" style="clear: both; text-align: center;"><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg93zJ5DasHEVEMOyFePPiR2Whd7810JhIDytpIUP1_uKl5NVQUstmEtlvBG8cs_m6p5fGySUVblWnA5-n9lBCyHZkjzpSzEqP2MUKrw1MyJyawvqkO2Sj5cLvYLrZGDX2REt1-03gancRymPq0A0qGfiE-Y1nHzoU4LtbVT86m_6nQ5eqCJS7SrA/s1322/TiddlyMap_KG_02042024.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="728" data-original-width="1322" height="352" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg93zJ5DasHEVEMOyFePPiR2Whd7810JhIDytpIUP1_uKl5NVQUstmEtlvBG8cs_m6p5fGySUVblWnA5-n9lBCyHZkjzpSzEqP2MUKrw1MyJyawvqkO2Sj5cLvYLrZGDX2REt1-03gancRymPq0A0qGfiE-Y1nHzoU4LtbVT86m_6nQ5eqCJS7SrA/w640-h352/TiddlyMap_KG_02042024.png" width="640" /></a></div><br /><br /></div><br /></li></ul>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-16589821900590148772024-02-03T06:00:00.000-05:002024-02-03T06:00:26.972-05:00Seeking Scalable Solutions in Systems<p>I started a little writing and cognition experiment which involves writing down a thought a day. We have about 6000 thoughts every day. A few are possibly worth capturing. I am not bothering with defining what's truly worth sharing -- this is a public blog after all -- but I suspect there will be some informal filtering in the absence of a clearly defined strategic intent. </p><p>Today's thought, or train of thoughts started when I opened a book and read a passage about the role of digital technology in making trash collection more efficient with sensors that detect when a trash bin is full. In principle, this creates efficiencies by allowing trash collection services to be more targeted and avoid wasting time, fuel, etc.. on trash bins that are empty or not full enough for pick up. </p><p>The main issue I had with this approach is that it attempts to address a problem downstream, after the trash has already been generated. It does nothing to reduce the amount of trash in the first place. The book I had opened is from 2016, so already potentially outdated. I looked up more recent technology solutions associated with waste management and found solutions that are looking more broadly and addressing a combination of issues related to waste management. Some cities have established weight-based or volume-based billing for trash pickup, which should encourage waste reduction (and potentially create illegal dumping issue). A combination of sensor technology and AI can now automatically sort trash for recycling purposes. <br /><br />Solutions that address a single node within a system could be very successful in addressing the problem at that node yet fail to address the broader issue or even displace the issue to other nodes in the system. So, part of the solution would be to look at the whole system. Given that ultimately, everything is connected to everything else, what is the most appropriate scope of the waste management system. At what point is the scope too broad? What is the trash that creates the most challenges? Is it plastics? How do we reduce plastics in trash? That probably requires interventions upstream, in the production of items that result in plastic trash. How do we determine the scope of a system?</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjA8Qs6LIpmRTxwu8lUccPZ_TKv60EZLSYBXi5tAK2wGuG7U0J_aqnN9U7NYfdikl9GPHAEu3GCFN2ImKcBxIt6gqirfbUNzYUeRhsMNPQ7crMjQnRcyLHrJgLn7hBcLWwJyZj37IzwXJdRkhuXLvdRHvXv9gTme2KDp65mjUYxsjYsrTycgOPNBQ/s2872/Systems%20Thinking%20for%20Scalable%20Solutions.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="2204" data-original-width="2872" height="308" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjA8Qs6LIpmRTxwu8lUccPZ_TKv60EZLSYBXi5tAK2wGuG7U0J_aqnN9U7NYfdikl9GPHAEu3GCFN2ImKcBxIt6gqirfbUNzYUeRhsMNPQ7crMjQnRcyLHrJgLn7hBcLWwJyZj37IzwXJdRkhuXLvdRHvXv9gTme2KDp65mjUYxsjYsrTycgOPNBQ/w400-h308/Systems%20Thinking%20for%20Scalable%20Solutions.jpg" width="400" /></a></div><br /><p><br /></p><p>The same thought applies in international development projects. These projects typically address a small slice of a problem within a node in a complex system. </p><p><br /></p><p><br /></p><p><br /></p><p><br /></p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-54011824949923294442024-02-02T17:05:00.004-05:002024-02-02T17:05:48.700-05:00Knowledge Cast - Barbara Fillip<p>I was invited as a guest of the <a href="https://enterprise-knowledge.com/knowledge-cast-barbara-fillip-of-chemonics-international/" target="_blank">Knowledge Cast podcast in December </a>and had a nice conversation with Enterprise Knowledge CEO Zach Wahl. <br /><br />We talked about knowledge management, of course. Somehow I ended the conversation by encouraging people to think about their own personal knowledge management habits. It wasn't planned but I'm glad I ended with that as a key lesson.</p><p><br /></p><p><br /><br /></p><p><br /></p><p><br /></p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-91357577400916051512024-02-02T05:52:00.000-05:002024-02-02T05:52:47.328-05:00KM, AI and Onboarding<p>My new KM+AI GPT-based news aggregator pointed me to this "guest post": <a href="https://blog.empuls.io/knowledge-management-system/" target="_blank">How Can Knowledge Management Systems Help in Faster Onboarding Of Employees</a>, 2/1/2024. These types of articles, potentially written by generative AI and meant to advertise related software, are not that insightful but they are useful as daily thinking/writing prompts. </p><p>There is no doubt a great opportunity to leverage KM and AI in support of onboarding. Organizational silos can get in the way if the KM function is focused on other perceived need.</p><p>Onboarding is a critical touch point to socialize KM, starting with basics of document management, an understanding of where the key knowledge bases are located and how to access them, including how to access people's knowledge via collaboration tools -- and when to use what tool.</p><p>An initiative to integrate KM and AI into a new onboarding strategy would undoubtedly reveal weaknesses in information infrastructure, data management, etc.. When you improve access to key resources for new employees, you improve access and awareness for all employees. Every weakness in existing systems that would surface as a result of a new onboarding strategy, if addressed properly, would have a huge impact on the entire organization. So, perhaps that looks like scope creep, but it needs to be done anyways. Might as well plan it in phases and get it done. </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-88284533410603472982024-02-01T05:42:00.000-05:002024-02-01T05:42:05.709-05:00Keeping up with AI<p>It would be an understatement to say that keeping up with AI developments is challenging. One of the challenges is to keep away from the daily announcements of new tools and capabilities and focus on underlying changes brought about by the availability and usability of these tools for the average person, whether within the organization or as an individual operating on their personal computer.</p><p>I've come to the conclusion that it is professional suicide to wait for employers to provide the tools so you can at least learn what it's all about. The organization will need time to safely integrate these tools within the technology ecosystem. I'm not suggesting anyone bypass their employer's guidance around use of AI, but we should all learn to use AI safely and responsibly, at home and at work. </p><p>Most people are likely dabbling with generative AI tools. It takes more than dabbling to become proficient and yield the most benefits. It will take more than dabbling to set up efficient tools within organizations. I am doing some intentional dabbling on my own but would not call myself an expert prompt engineer just yet. </p><p>One way to keep up with AI news is to use AI to simplify the task by creating a GPT designed to bring up news about AI -- or any subject for that matter. This is the equivalent of a news aggregator but instead of a list of links, it provides a neat, short summary of the content of the items, and a link (or an indication of the source). I created a GPT that, when prompted, gives me about 5 news items from the past 48 hours related to AI and Knowledge Management. It has led me to some interesting things I would never have come across based on my routine sources of news. </p><p>When I prompted the ChatGPT 4 with a similar query, it gave me completely different answers. That is not surprising at all. Even asking ChatGPT the same thing twice would probably yield different answers. The biggest difference is that with the tailored GPT, I am able to identify the main sources of information to focus on and even though it is not always pulling from those resources, the results are much more "on target" than with ChatGPT. <br /><br />So, the pre-prompting of GPTs is critical in creating more precise boundaries for the data to be used by the AI in the development of an answer. At the same time, it has the advantage of an LLM. </p><p>There are also a lot of AI developments that won't affect us directly as employees or individuals outside of work but that we should consider as we design future projects and activities. The breadth of AI-generated data that may become available needs to be accounted for. For example, reading this article, "<a href="https://phys.org/news/2024-01-artificial-intelligence-pollution-air.html" target="_blank">Using artificial intelligence, better pollution predictions are in the air</a>," it struck me that international development projects will need to plan for enhanced capacity to utilize these new sources of data and project implementors may be able to develop more precise models and Theories of Change based on more sophisticated AI-enhanced models.<br /><br />In short, we all need to go beyond dabbling in generative AI. </p><p><br /></p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0tag:blogger.com,1999:blog-5296831.post-57798253719191089132023-03-11T07:15:00.006-05:002023-03-14T05:29:06.490-04:00Playing with ChatGPT and Understanding How to Query ChatGPT<p>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.</p><p>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. </p><p>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 <b>conversation</b> 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. <b> It is probabilistic model</b>. 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. </p><p>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.</p><p>Here are a few questions I asked:<br /></p><ul style="text-align: left;"><li>What are the main uses for a World Café? </li><li>Is it different from a Knowledge Café? -- I learned a few nuances I was not aware of.</li><li>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.</li><li> 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. </li><li>When is a World Café or Knowledge Café the most appropriate way to engage a group of people in a meaningful conversation?</li><li>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. <br /></li></ul><div>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:<br /><ul style="text-align: left;"><li>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?</li></ul><div>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.<br /><br />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. <br /><br />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.<br /><br />So I asked a follow up question: "What about participants?" YES. Very good answer to that. </div></div><div><br /></div><div><b>Final question: </b> 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". <br /><br /><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEhN9rdTTGA69MkO6RDs-XBt7wpPEa2im9X1dKqbgIutW_BT3_cWech1xVm-rAUXZsmspS9z7xcahBuC93Zbzl_sUfGw-fw9xI5H_QwfhHLIxFhCK48MtjaLKuBv2Sv9GoRBpa2iGyxSRNMdOrtRJyVJPZsDVYlWHzeDBnUWr_MT8anesUHZjq0" style="margin-left: 1em; margin-right: 1em;"><img alt="" data-original-height="60" data-original-width="662" height="58" src="https://blogger.googleusercontent.com/img/a/AVvXsEhN9rdTTGA69MkO6RDs-XBt7wpPEa2im9X1dKqbgIutW_BT3_cWech1xVm-rAUXZsmspS9z7xcahBuC93Zbzl_sUfGw-fw9xI5H_QwfhHLIxFhCK48MtjaLKuBv2Sv9GoRBpa2iGyxSRNMdOrtRJyVJPZsDVYlWHzeDBnUWr_MT8anesUHZjq0=w640-h58" width="640" /></a></div><br /></div><p></p><p>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. </p><p><b>Lesson Learned with this set of ChatGPT queries:</b></p><p></p><ul style="text-align: left;"><li><b>Smart querying requires critical thinking</b>. 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.</li><li><b> Don't give up too quickly</b> 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. </li><li><b>Keep an eye on the full query</b>, 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. </li><li><b>There is a lot I don't understand</b> 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. </li></ul><div>Read also:</div><div><ul style="text-align: left;"><li><a href="https://realkm.com/2023/03/11/chatgpt-is-great-youre-just-using-it-wrong/">ChatGPT is great – you’re just using it wrong – RealKM</a></li></ul></div><p></p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.comtag:blogger.com,1999:blog-5296831.post-7830920435749632032023-02-04T07:40:00.003-05:002023-02-04T07:40:40.333-05:00Change and Knowledge Management<p>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?</p><p>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. </p><p>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. </p><p>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. </p><p>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. </p><p>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.</p><p>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.<br /><br />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?</p><p></p><ul style="text-align: left;"><li>Listen</li><ul><li>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?</li><li>Listen outward: Read up and stay informed about external development. </li></ul><li>Engage</li><ul><li>Engage {gently} to correct misunderstandings.</li><li>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.</li><li>Prompt leadership to engage (as needed). </li></ul><li>Support <br /></li><ul><li>Based on listening and engaging, determine where KM fits in, how the KM team (often a team of one) can support;</li><li>Engage more deeply with key stakeholders who will lead the charge in terms of "managing" the change. </li><li>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). <br /></li></ul></ul><p></p><p>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. </p>Barbara Filliphttp://www.blogger.com/profile/05037721407696917441noreply@blogger.com0