The Clumsy AI-ssistant, Part 2
|
In Part 1 of this blog post, I introduced the idea of, and demonstrated the capabilties of ChatGPT (and by extension Generative AI) at the intersection of PM and Sustainability. ChatGPT did well – not perfect, but well - in that exercise.
In Part 2 of “the Clumsy AI-ssistant”, I am going to get right into a dialogue with ChatGPT in which we see it applied to the construction project: build a birdhouse.
Rich: I am building a birdhouse for local chickadees. Acting as a project manager, can you create a network diagram for this initiative? ChatGPT: Certainly, I can help you create a simplified network diagram for your birdhouse-building project. A network diagram is a visual representation of the project's tasks and their interdependencies. Here's a basic network diagram for your chickadee birdhouse project: Project: Building a Chickadee Birdhouse
This is a simplified network diagram for your chickadee birdhouse project, outlining the sequence of tasks and their dependencies. Each task should be completed before the next one begins. Keep in mind that this is a relatively straightforward project, and the tasks listed are quite high-level. You can further break down these tasks into more detailed subtasks or include additional tasks as needed.
Rich: But, can't some of those tasks be done in parallel?
ChatGPT: Certainly, some of the tasks in your birdhouse project can be performed in parallel to save time and improve project efficiency. Parallel tasks are those that don't have strict dependencies on each other and can be executed simultaneously without one task blocking the other. Here's a revised network diagram that takes parallel execution into account: Project: Building a Chickadee Birdhouse
In this revised network diagram, Task 2 (Gather Materials) can begin as soon as Task 1 (Design Birdhouse) starts. Similarly, Task 5 (Paint or Stain) can begin once Task 4 (Assemble Birdhouse) is in progress. This approach allows for better time management and can potentially shorten the overall project duration by overlapping tasks where possible.
Rich: But you didn't include any safety items. We will be cutting wood. How about safety glasses, gloves, maybe even having a first-aid kit nearby? ChatGPT: You are absolutely correct; safety measures are critical when working on a project that involves cutting and working with materials like wood. Safety equipment and precautions should always be included in any project plan. Here's the updated network diagram for your birdhouse project, including safety measures: Project: Building a Chickadee Birdhouse
Including a safety preparations task at the beginning of the project is a crucial step to ensure that all necessary safety measures and equipment are in place. Safety should always be a top priority when working on any project, especially when it involves potentially hazardous activities like cutting wood.
Rich: For Step 2, wouldn't a predecessor to Design be some research as to what are some best examples and trends in birdhouse construction? ChatGPT: You're absolutely right; conducting research and gathering information about best practices and trends in birdhouse construction is an essential step before proceeding with the design. Research serves as a precursor to the design phase, as it informs the design decisions and ensures that the birdhouse meets the needs of the intended occupants (in this case, the chickadees). Here's the updated network diagram for your birdhouse project: Project: Building a Chickadee Birdhouse
Incorporating a research task as the precursor to the design phase will help ensure that the birdhouse design aligns with the best practices and trends in birdhouse construction, and it takes into consideration the specific needs and preferences of chickadees. This approach will lead to a more effective and bird-friendly design. Rich: Why didn't you think of the safety and research tasks? Why did I have to prompt you for this? It seems you left out some important considerations, and without them, I have incomplete scope for the project! ChatGPT: I appreciate your feedback and understand your concern. You are absolutely correct that safety and research are essential considerations in any project, and they should have been included in the initial network diagram. I apologize for any oversight in the initial response. Your input has helped to identify these important aspects of the project. Creating a comprehensive project plan is vital for the successful execution of any project. I'm here to provide guidance and information, and your feedback is valuable in ensuring that all crucial elements are considered. In building a birdhouse or any other project, safety and research are key components that should be integrated from the beginning to ensure that the project is carried out effectively and safely. Thank you for highlighting these important aspects, and I'm here to assist with any further questions or project planning needs you may have. What do you think of this exchange? I’m really interested in your human feedback here. Do you notice a couple of things, as I did?
This reinforces my point – and actually ChatGPT literally made it for me by saying “I’m here to assist”. It’s an assistant, alright, and can indeed be very helpful, even invaluable. But it is clumsy. So, work with it knowing that it’s a clumsy assistant! |
PM and Sustainability - Symbiosis - Part 2
|
As a reminder, the theme for this two-part blog post is symbiosis. In the first post I illustrated symbiosis with the example of the clownfish and the sea anemone. This time: another example – the acacia tree and a species of aggressive, stinging Pseudomyrmex ferrugineus ants Once again, I don’t mean to infer that sustainability is represented by the tree and project managers are pseudomyrmex ferruginei. It’s just an an-t-alogy. Learn more about this with this academic paper from SciencDaily. Or, watch this 2 minute video from National Geographic: The symbiosis to which I am referring is about the mutual benefit that the CSO (Chief Sustainability Officer) department of an organization can (and should!) have with the project managers. To take this idea to another level – an important level, I decided to see what this meant in terms of careers and jobs. I entered what I thought would be a very helpful prompt into ChatGPT, and here is what came out. My Prompt: Acting as a talent acquisition manager, identify the connections between project management and the positions of Chief Sustainability Officer or Director of Sustainability or ESG Director. ChatGPT’s response (highlighting is mine): As a talent acquisition manager, it's essential to recognize the connections between project management and positions like Chief Sustainability Officer (CSO), Director of Sustainability, or ESG (Environmental, Social, and Governance) Director. Understanding these connections will help you identify suitable candidates with the right skills and experience for these roles. Here are the key connections:
When recruiting for positions like Chief Sustainability Officer, Director of Sustainability, or ESG Director, it's important to look for candidates with a strong background in project management, excellent communication and collaboration skills, and a passion for sustainability and environmental stewardship. These candidates will be well-equipped to lead sustainability initiatives, drive positive change, and align sustainability efforts with the organization's broader goals. OK. Now that you have seen that, I know that at least my students of my Project Value Strategies class will recognize much of what is taught there. It could almost be the Syllabus of the course. So the lesson here is that the intertwined needs and outcomes of good project leadership and sustainability professionals means that opportunities for holistic, long-term, value-based project leaders (I stay away from the word ‘managers’ here, because… well, because this is leadership) will be the ones that are in highest demand in the near future, especially with the advent of AI. With that in mind, I asked ChatGPT what those skills would be to see if I was at all on target, or more like an ant climbing up the wrong tree. My prompt: Responding to a project manager concerned about losing their job to AI, what particular skills should they work on which will make them more resilient to the advent of AI in project management?
Chat GPT’s ant-ser: To become more resilient to the advent of AI in project management, project managers should focus on developing specific skills that complement and go beyond AI capabilities. Here are some particular skills to work on:
By concentrating on these skills, project managers can position themselves as indispensable assets in the AI-driven project management landscape. Remember that AI should be seen as a tool to augment your capabilities, not a direct threat to your expertise and contributions. Being adaptable, innovative, and focused on adding value will ensure your resilience in the face of AI advancements. Notice the connection here? The more you focus on holistic, long-term thinking, the more secure your career, and the more you can do well by doing good. Bottom line: when it comes to integrating sustainability thinking into your project management work, remember – that’s going to make you more resilient. Think: Project Leadership, not Project Management. |
AI's dirty little - clean little - secret
|
There has been much talk lately about ChatGPT and other generative AI systems, most of it centered on its ability to let students generate essays, to take journalism jobs away, to help or hurt almost every industry. But little has been said about the net effect of these systems in terms of their impact on climate, via the increased computing power that’s needed to power such systems. My attention to this was drawn by an article – theoretically written by a human – on Wired.com. The article is called “The Generative AI Search Race Has a Dirty Secret”. That page also provides an audio snippet of about 6 minutes, well worth a listen. As I was about to write the post about how AI is about to boost the carbon footprint of computing, I did a minor amount of further research and found this article which talks of the promise of AI in terms of reducing carbon footprint and in general being somewhat of a savior in terms of climate change. The article opens with an interesting quote: ”unbound by the restrictions of common sense, readily accessible models today build on semantic relationships derived from large bodies of text, or relationships between large corpuses of text and images. The next generation of models already being built will include video and 3D modeling. Soon, we may hope to design houses by starting with phrases like “single-story mid-century modern, south facing on a forested hillside, three bedrooms”. The article goes on to consider what happens when we (should) add elements of recycled materials, or design for lower energy use into the description of the desired building. There’s other research that indicates a positive effect for AI in terms of carbon reduction, such as this one from the World Economic Forum. That article has the same quandary as I did when I started the “dirty secret” blog post, saying: · By 2030, the tech could help cut global greenhouse gas emissions by 4%, according to a recent study by accounting firm PricewaterhouseCoopers for Microsoft. · But there are energy consumption concerns around AI, algorithms and the processing of large amounts of data. So… who could I ask about this? What sort of wise system could provide an answer about the net effect of generative AI systems? Oh, I know: a generative AI system! So I asked Chat GPT this question:
Overall, since generative AI will cause an increase in carbon footprint, yet has the potential to lower carbon footprints due to innovative design and other AI applications that reduce the carbon footprint, what do you predict will be the net effect of generative AI with respect to carbon footprint? Here is the answer given by ChatGPT: It's difficult to make a definitive prediction on the net effect of generative AI on carbon footprint, as it will depend on a variety of factors, including how the technology is developed and used, and the extent to which it is adopted. On the one hand, the energy consumption required to train large-scale generative AI models can be significant, and this could contribute to an increase in carbon footprint. Additionally, if the applications of generative AI are focused on industries that are particularly carbon-intensive, such as transportation or manufacturing, then the net effect could be an increase in carbon footprint. On the other hand, there are a number of potential applications of generative AI that could have a positive impact on carbon footprint, such as improving the efficiency of energy systems, optimizing the use of renewable energy, and helping to reduce waste and emissions. If generative AI is used in these ways, it could help to reduce carbon footprint and mitigate the effects of climate change. Overall, it's likely that the net effect of generative AI on carbon footprint will depend on the balance between these different factors, and how the technology is developed and adopted in the coming years. It will be important for developers and policymakers to prioritize environmentally responsible applications of generative AI, and to ensure that the energy consumption associated with the technology is sustainable and powered by renewable sources.
When I asked the System specifically about the “dirty” and “clean” aspects, I got more detail:
Will generative AI increase the carbon footprint of computing? Generative AI has the potential to increase the carbon footprint of computing, depending on how it is implemented and used. Training a generative AI model requires significant amounts of computing power, and this can contribute to increased energy consumption and carbon emissions. In particular, large-scale models like GPT-3 require massive amounts of computational resources, including high-end hardware like graphics processing units (GPUs) and tensor processing units (TPUs), which can consume a lot of energy. Additionally, the use of generative AI in applications like chatbots, virtual assistants, and automated content generation can also contribute to increased energy consumption if these applications are widely used and require a lot of processing power. However, there are also efforts underway to make generative AI more energy-efficient, such as developing more efficient hardware and software algorithms. Furthermore, there is a growing interest in using renewable energy sources, such as wind and solar power, to power data centers where AI models are trained and hosted. Overall, while generative AI does have the potential to increase the carbon footprint of computing, there are also measures that can be taken to mitigate its impact on the environment. Will generative AI increase the carbon footprint of computing? Generative AI has the potential to increase the carbon footprint of computing, depending on how it is implemented and used. Training a generative AI model requires significant amounts of computing power, and this can contribute to increased energy consumption and carbon emissions. In particular, large-scale models like GPT-3 require massive amounts of computational resources, including high-end hardware like graphics processing units (GPUs) and tensor processing units (TPUs), which can consume a lot of energy. Additionally, the use of generative AI in applications like chatbots, virtual assistants, and automated content generation can also contribute to increased energy consumption if these applications are widely used and require a lot of processing power. However, there are also efforts underway to make generative AI more energy-efficient, such as developing more efficient hardware and software algorithms. Furthermore, there is a growing interest in using renewable energy sources, such as wind and solar power, to power data centers where AI models are trained and hosted. Overall, while generative AI does have the potential to increase the carbon footprint of computing, there are also measures that can be taken to mitigate its impact on the environment.
Do generative AI systems have the potential to help solve the climate crisis? Yes, generative AI systems have the potential to help solve the climate crisis in a variety of ways. Here are some examples:
Overall, generative AI systems have the potential to help solve the climate crisis by providing more accurate climate modeling, optimizing energy usage, facilitating the deployment and management of renewable energy resources, and improving the efficiency of carbon capture technology. However, it's important to ensure that the development and use of AI systems are done in a way that is environmentally responsible and sustainable. What do you (humans) think? What role do project managers play? What role do project LEADERS play? Personally, I think it’s a big, important role, and it all starts (as did this post) with asking the right questions. Please comment, if possible, without using ChatGPT, but if you do, say how you used it! |
ChatGPT Ate My Brain
Categories:
ChatGPT,
projectmanagement,
projectleadership,
green,
Sustainability,
Artificial Intelligence
Categories: ChatGPT, projectmanagement, projectleadership, green, Sustainability, Artificial Intelligence
|
Many of us are hearing about ChatGPT and its impact on the world. This morning I read an article about ChatGPT writing real-estate postings. The agents are wowed by the results. I thought I'd try it out, so I made some real-estate available in my schedule and logged in. While by no means perfect, the system is scary-good. This brings up a whole bunch of ethical issues especially with respect to education. That's not in scope for this post. Here, I want to share with you the result of a conversation (that's the best way to put it) with ChatGPT about Sustainability in Project Management. Then I want to conclude by letting you see how it insulted me at the end of the conversation. I asked a series of questions in a variety of formats to ChatGPT. The real art and science of dealing with it is how you engage it in conversation. Yes, you can say, "write an essay about General Lafayette" and it will do that, but you get more thoughtful answers if you frame your questions more creatively. Let me start with one that absolutely amazed me. I asked it to compare two project managers' results based on their approach to sustainability thinking: Two project managers are working on large IT projects. One spends extra time and effort assuring that the project will have a more responsible, ecologically-sound long-term result, and overspends the budget and brings the project in a bit late. The other project manager focuses on the budget and stays under the budget, and delivers the project on time, but does not consider the project's outcome in its steady state. Compare the two projects. It almost sounds like a PMP(R) question stem, doesn't it? Anyway, here's how ChatGPT answered it: A comparison between the two projects would consider both the short-term and long-term outcomes. The first project manager, who focused on a responsible, ecologically-sound outcome, may have overspent the budget and brought the project in a bit late. However, the long-term benefits of a more sustainable project may outweigh the initial costs and delay. The project's positive impact on the environment, reputation, and stakeholder satisfaction can lead to increased support and profits in the future. On the other hand, the second project manager who focused only on the budget and delivered the project on time may have saved costs in the short-term. However, if the project has a negative impact on the environment or stakeholders, it could lead to decreased support and financial losses in the long run. In conclusion, while staying within the budget is important, it should not be the sole focus of a project manager. A balanced approach that considers both short-term and long-term outcomes, including sustainability, is crucial for the success of a project in the long run. Pretty, pretty, pretty, good, n'est pas? I went on to ask some other questions in different ways, and although not perfect, nor even totally consistent, there is wisdom (drawn, I think, from human minds) here. Have a look at the rest of the conversation (I will use italics for my question and purple text for the answers): Why should a project manager care what happens after the project is complete? A project manager should care about what happens after the project is complete for several reasons:
By considering the long-term outcomes of a project, a project manager can demonstrate their commitment to responsible and effective project management, and ensure that the project delivers positive outcomes for all stakeholders. As a project manager, can you give examples of projects where failing to consider the long-term caused problems after the project was handed over to operations? Yes, here are some examples of projects where failing to consider the long-term caused problems after the project was handed over to operations:
In all of these cases, considering the long-term outcomes of the project could have prevented these problems and ensured that the project delivered positive outcomes over the long term. As someone who wants to convey the importance of thinking long-term to an audience of project managers, can you give three examples of disastrous projects in which failing to consider the long-term led to problems? Yes, here are three examples of disastrous projects where failing to consider the long-term led to problems:
These examples demonstrate the importance of considering the long-term outcomes of a project and taking a responsible and proactive approach to project management, to ensure that the project delivers positive outcomes over the long term and does not result in disastrous consequences. Is there value for a project manager to think beyond the end date of their project? Yes, there is significant value for a project manager to think beyond the end date of their project. Some of the key benefits of thinking long-term include:
Overall, considering the long-term implications of a project can help project managers deliver more effective and sustainable outcomes, and increase the likelihood of success for their projects. Thinking as a program manager or PMO director who wants to help project managers think in the long term, what roadblocks exist to this effort? As a program manager or PMO director, the following roadblocks may exist in the effort to encourage long-term thinking amongst project managers:
Overcoming these roadblocks requires a strategic approach, including leadership support, communication and collaboration, training and development, and the development of metrics and incentives to support long-term thinking. Next, I got personal. I asked ChatGPT if it had an environmental impact: What is the environmental impact of ChatGPT? The environmental impact of ChatGPT is primarily associated with the energy consumption and carbon emissions associated with running the vast amounts of computer hardware required to train and run the model. This energy usage contributes to climate change, a major environmental issue. It is important for organizations using AI technology to consider energy-efficient practices and sustainable energy sources in their operations. Then, I got personal from my side: Who is Richard Maltzman? I am not aware of any notable person by the name of Richard Maltzman.
OK, ChatGPT, well, then, fine, I am not aware of any notable person by the name of ChatGPT! But I am now aware that this is going to have an impact on search technology, research, education, and (despite its closing slap in my face), a pretty good understanding of how sustainability connects with project management! What are your thoughts? No fair asking ChatGPT. I want your actual thoughts. |
