Jul 14 2023
Start of the series on AI and L&D
This is the start of a series on AI in L&D. The series is exploring what people are doing now with AI, what people are thinking about, and what people are learning.In this episode, we kick off the series where Robin does an interview with ChatGPT on transforming learning at work. The voice is generated by ElevenLabs.If you are interested, it might be easier to read the blog post along with the podcast, than listening to the computer generated voice.Key takeaways:Promoting self-guided learning and automation in instructional design can contribute to a culture of continuous learning. Automation can be used in instructional design to automate routine tasks and increase efficiency, such as AI automating content curation, learner data analysis, and feedback collection and analysis.There are risks and considerations to be aware of when using AI. These include the dangers of dependency on AI, the digital divide in access to AI tools, ethical concerns regarding biassed information, and the importance of data privacy. To address these risks, organisations should comply with data privacy laws, implement quality control measures, balance AI with human-led learning experiences, and provide training and support for employees who are not comfortable with technology.Strategies for using AI in workplace learning include having human mentors or instructors for discussions and social learning opportunities, providing training and support for employees who are not comfortable with technology, and incorporating ethical considerations when choosing AI providers.Segmented time stamps:(00:00) The argumentation of human lead learning(01:58) AI in workplace learning(05:35) Adaptive learning experience pathways(08:15) On-demand learning for safety leadership(11:41) Content curation and updates(16:07) The risks of using AI in L&D(21:33) The role of humans and AI in the workplace(24:53) Balancing the use of AILinks from the podcast Check out ElevenLabsTranscript:Robin: Act as an expert on L&D and learning. You're going to be a guest on the Learning While Working podcast. The audience is workplace L&D professionals. The interview is going to talk about how you (chatGPT) can transform learning at work. I'm going to ask you questions.ChatGPT: Sure, I'd be happy to participate in this mock podcast interview. Feel free to start with your questions.Please remember that while I can provide useful and insightful information, I'm an AI model developed by OpenAI and my responses are based on patterns in the data I was trained on, up until September 2021. Any information or insights I provide should be validated and adapted to your specific context.Robin: Welcome to the Learning While Working podcastChatGPT: Thank you for having me on the Learning While Working podcast. It's an exciting opportunity to connect with the L&D community. As an AI developed by OpenAI, I aim to provide insights and information that can help transform learning at work. Let's get started!Robin: What are 3 ways you transform learning at work?ChatGPT: AI, such as myself, can help to transform learning at work in various ways. Here are three significant ways:Personalised Learning: One of the biggest challenges in workplace learning is meeting the diverse needs of learners. AI can analyse an individual's learning style, previous knowledge, and performance data to deliver personalised learning experiences. For instance, based on a learner's progress, AI can recommend next steps, additional resources, or even a change in learning strategy to improve outcomes.On-Demand Learning: The traditional model of set training times and classrooms isn't flexible or scalable, especially in a world where remote work is increasingly common. AI can provide on-demand learning, allowing employees to learn at their own pace, anytime and anywhere. This is especially useful for quickly updating employees on new tools, policies, or industry developments.Automation of Routine Tasks: A lot of L&D professionals spend considerable time on administrative tasks like scheduling training sessions, tracking progress, and generating reports. AI can automate these routine tasks, allowing L&D professionals to focus more on strategic tasks such as designing better learning experiences and interventions.These are just a few examples of how AI can help. The actual impact will depend on the organisation, its culture, and its readiness to leverage AI in learning and development.Robin: Give me three examples of Personalized Learning?ChatGPT: Certainly, personalised learning through AI can take many forms. Here are three specific examples:Adaptive Learning Paths: AI can create adaptive learning paths based on each learner's knowledge level, skills, and learning speed. For instance, if an employee is already proficient in certain areas, the AI can automatically adjust their learning pathway to focus on areas where they need improvement. This avoids wasting time on content they already know and focuses on developing areas where they need growth.Recommendation Systems: Similar to how Netflix or Amazon recommends movies or products based on past behaviour, an AI can recommend learning resources based on a user's past learning behaviour and performance. For example, if a user struggled with a particular concept, the AI might suggest additional resources, such as videos or articles, to reinforce their understanding.Learning Style Adaptation: AI can adapt the format of the content to match the learner's preferred style. For example, some people learn better through visual materials like infographics and videos, while others prefer text-based resources or interactive simulations. AI can track how users interact with different types of content and then prioritise delivering content in the formats that work best for them.In all these ways, AI can help create a personalised, more engaging, and effective learning experience for each individual.Robin: You're being a bit vague. Give me and example of using ChatGPT for Adaptive Learning Paths for cybersecurity skills.ChatGPT: Certainly, let's take a more detailed look at how ChatGPT could be utilised for creating an adaptive learning path in the field of cybersecurity.Suppose an employee, let's call her Jane, is tasked with improving her cybersecurity skills. After an initial assessment or quiz, it's clear that Jane has a strong understanding of basic concepts such as types of threats and fundamental security protocols, but she struggles more with advanced topics like incident response management and network security.Initial Assessment: In this scenario, ChatGPT could begin by providing an interactive assessment, where Jane answers questions or solves problems related to various aspects of cybersecurity. This could involve everything from basic concepts to more advanced ones.Custom Learning Pathway: Based on Jane's performance on the assessment, ChatGPT identifies her strengths and weaknesses. Since she already has a strong understanding of basic concepts, the AI doesn't include these topics in her learning pathway. Instead, it prioritises advanced topics like incident response management and network security.Learning Delivery and Continuous Assessment: As Jane moves through her personalised learning pathway, she interacts with ChatGPT in a conversational manner, discussing cybersecurity scenarios, answering quiz questions, and solving problems related to her learning topics. ChatGPT adjusts the complexity and depth of the content based on Jane's progress.Regular Feedback and Adjustments: Throughout this process, Jane receives instant feedback on her progress, which helps her understand where she stands and how she's improving. If Jane is struggling with a certain topic, ChatGPT might choose to slow down, provide additional learning resources, or approach the topic from a different angle.In this way, ChatGPT can provide a flexible, responsive learning experience that adapts to Jane's needs, ensuring she focuses on the areas where she needs to grow most.This approach not only saves time by avoiding unnecessary repetition of known topics but also promotes engagement and effective learning by focusing on areas of need and providing instant feedback.Robin: This is good. How about an example for On-Demand Learning for safety leadershipChatGPT: Absolutely. Here's how ChatGPT could provide on-demand learning for an area such as safety leadership:Let's consider a manager, we'll call him John, who has been tasked with improving his safety leadership skills to better lead his team in a manufacturing environment. John works on a tight schedule and he often can't participate in traditional training programs during usual business hours.24/7 Availability: Since ChatGPT is an AI, it is available 24/7. John can interact with the training program whenever he has time, be it early in the morning before his shift starts, or late in the evening after he finishes his work. He doesn't have to wait for a scheduled training session.Learning in Context: Suppose a specific situation arises at work that John is unsure how to handle from a safety leadership perspective, like responding to a safety incident. He could immediately consult with ChatGPT, asking specific questions to learn how to best handle the situation. ChatGPT could provide guidance based on best practices in safety leadership, and provide resources for deeper learning.Role-Playing Simulations: On-demand learning isn't just about reading material or answering quiz questions. For example, John could engage in a role-playing scenario with ChatGPT at any time, where he has to navigate a simulated safety incident, make decisions and respond to changes. This on-the-spot, interactive learning can be highly effective for building practical skills.Just-In-Time Learning: If a new safety regulation or procedure is implemented, John can immediately get the necessary training from ChatGPT. It can provide an overview of the new rule, explain its implications, and even quiz John to ensure he has understood the change.This kind of on-demand learning can be particularly effective because it is self-paced, flexible, and contextual. It allows learners to get the knowledge when they need it, apply it immediately, and therefore, they are more likely to retain it.Robin: Is this key to type experience making sure employees are self guided learners?ChatGPT:Yes, fostering a culture of self-guided learning is a key aspect of successful implementation of AI-driven personalised and on-demand learning. Here's why:Ownership of Learning: When employees are self-guided learners, they take ownership of their learning journey. This makes the learning process more effective because they are actively seeking knowledge, rather than passively receiving it.Pace and Style: Self-guided learners can set their own pace and choose their preferred style of learning. This flexibility can lead to more engagement and better absorption of knowledge.Immediate Application: Self-guided learners can immediately apply what they've learned to their work, which can reinforce their learning and demonstrate its practical relevance.Continuous Learning Culture: Promoting self-guided learning can contribute to a culture of continuous learning. In today's rapidly changing work environment, continuous learning is crucial for businesses to stay competitive and for employees to keep their skills up-to-date.However, it's important to note that not everyone may be used to or comfortable with self-guided learning. In these cases, organisations can provide support and guidance to help employees become more self-directed learners. This could include training on how to use AI learning tools, creating clear learning paths for skills development, and providing mentors or coaches to guide learners.Robin: Getting those top 3 things. How could an instructional designer use Automation of Routine Tasks?ChatGPT: Absolutely. There are several routine tasks within instructional design that can be automated with AI, which can greatly increase efficiency and allow instructional designers to focus more on the creative and strategic aspects of their work. Here are three specific examples:Content Curation and Update: AI can automate the process of sourcing, organising, and updating learning content. For example, an AI could crawl the web or a specific database to find relevant articles, videos, or research papers for a particular course topic. It can also regularly check for updates or newer versions of the existing learning content and replace outdated materials.Learner Data Analysis: AI can automate the analysis of learner data to provide insights into learning behaviours and performance. For instance, AI could automatically generate reports on learner engagement, quiz performance, areas of struggle, and more. This allows instructional designers to quickly and efficiently evaluate the effectiveness of their courses and make data-driven improvements.Feedback Collection and Analysis: Collecting and analysing learner feedback is an important but time-consuming task. AI can automate this process by prompting learners for feedback at optimal times (like after a course completion), collating the feedback, and analysing it to provide actionable insights. It could categorise feedback into themes, identify common issues, and even suggest potential improvements.By automating these tasks, instructional designers can save significant time and focus more on designing effective, engaging learning experiences. Additionally, the insights provided by AI can inform their design decisions, leading to more effective learning outcomes.Robin: How about for content creation?ChatGPT: AI can indeed assist with content creation in a variety of ways, which can be particularly useful for instructional designers. Here are a few examples:AI-Powered Writing Assistants: Tools like ChatGPT can assist in drafting course content. Given an outline or a set of key points, AI can generate draft content, which can then be edited and refined by instructional designers. This can speed up the content creation process, especially for first drafts or when creating content in a specific area of expertise.Content Optimization: AI can analyse content and suggest improvements based on best practices. For example, it might suggest simplifying complex sentences, adding more visuals, or including quizzes and interactive elements at certain intervals to boost engagement and retention.Translation and Localization: If content needs to be provided in multiple languages, AI-powered translation tools can be used to translate the content. Additionally, AI can help localise content, i.e., adapt the content to fit the cultural, societal, and linguistic context of different learner groups.Creating Interactive Content: AI can help create interactive content such as quizzes, simulations, or even chatbots for role-playing scenarios. Instructional designers can input the learning objectives and key points, and the AI can generate appropriate interactive content.It's important to note that while AI can assist in content creation, the role of instructional designers remains crucial. They provide the human touch, the deep understanding of learner needs, and the creativity that AI cannot replicate. AI should be seen as a tool that can augment the capabilities of instructional designers, not replace them.Robin: What are some risks of using you for workplace learning?ChatGPT: Using AI like ChatGPT for workplace learning presents several opportunities but also comes with some risks. It's important to consider these potential challenges:Data Privacy: AI platforms often rely on data from users to provide personalised experiences. This can raise concerns about data privacy, particularly if sensitive information is involved. It's crucial to ensure that any AI used in the workplace complies with data privacy regulations and that users are informed about how their data is used.Quality Control: While AI can generate content and assist with learning, the quality of that content may not always meet the necessary standards. Misunderstandings or inaccuracies could lead to the dissemination of incorrect information, which could be particularly harmful in areas such as safety training or compliance.Dependency: There's a risk that organisations could become overly reliant on AI for learning and development, neglecting the importance of human interaction and guidance in the learning process. While AI can deliver information and even personalise learning to some extent, it can't replace the mentorship and social interaction that humans provide.Digital Divide: While AI can offer powerful tools for learning, not all employees may have equal access to these tools. For example, employees who are not comfortable with technology or who lack access to high-quality internet may not benefit as much from AI-based learning tools.Ethical Considerations: AI systems, including ChatGPT, are trained on vast amounts of data, which can include biassed or prejudiced information. Even though measures are taken to prevent it, these biases can sometimes influence the AI's output. This is a broader issue with AI and machine learning and something to be aware of when using AI tools.It's crucial for organisations to be aware of these risks and to implement strategies to mitigate them when using AI for workplace learning.Robin: Can we just drill into Data Privacy? What are your Data privacy features?ChatGPT: As an AI developed by OpenAI, I am designed with privacy in mind. Here are some key aspects to understand about how I handle data:No Personal Data Storage: As of my training cut-off in September 2021, I don't have the ability to access or retrieve personal data from users unless it's shared with me in the course of our conversation. I don't store personal conversations or use them to inform my responses.Temporary Data Retention: By default, OpenAI retains data passed to the ChatGPT API for 30 days, but doesn't use it to improve my models.Privacy by Design: From the outset, I've been designed to respect user privacy. For example, I don't ask for personal data unless it's strictly necessary for the conversation.However, it's important to note that the usage of AI tools should still comply with the organisation's data privacy policies and any local laws or regulations. You should always be clear with employees about how their data is being used, and make sure you have their consent before using AI tools in a learning context.As data privacy is a dynamic field with constantly evolving regulations and standards, it's crucial to regularly review and update your data privacy policies and practices.Robin: But doesn't mean you're losing opportunities for training data?ChatGPT: While it's true that retaining and using conversational data could potentially provide opportunities for refining and improving AI models, OpenAI has chosen not to use data from individual interactions with ChatGPT to improve the model in order to prioritise user privacy and confidentiality.This decision reflects an important balance in AI development between improving the system and ensuring user trust. Given that AI systems like me are often used in contexts where sensitive or private information might be discussed, ensuring that users feel safe and confident that their data won't be used without their explicit permission is a critical priority.It's worth noting, though, that overall improvements in the model, which are based on extensive and diverse datasets, will continue to enhance the effectiveness and accuracy of the AI, benefiting all users.Robin: Going back to the risks you talked about, how can we overcome those risks?ChatGPT: Addressing these risks requires thoughtful planning and implementation. Here are some suggestions:Data Privacy: Ensure any AI tool used complies with all relevant data privacy laws and regulations, such as GDPR in Europe. Implement robust data protection measures, and be transparent with users about what data you collect, why you collect it, and how you use and protect it.Quality Control: Don't rely solely on AI for creating and delivering content. Always have a human in the loop to review and validate the information. Regularly test the system and provide opportunities for users to give feedback or report errors.Dependency: Balance the use of AI with human-led learning experiences. AI is a tool to supplement and enhance learning, not replace human guidance and interaction. For example, you might use AI for delivering content and personalising learning paths, but still have human mentors or instructors for discussions, mentoring, and social learning opportunities.Digital Divide: Provide training and support for employees who are not comfortable with technology. This might include basic digital literacy training or one-on-one support. Make sure your learning experiences are accessible on different devices and internet speeds, and where necessary, provide alternative, non-digital learning options.Ethical Considerations: Choose AI providers who are transparent about their training data and methods and who actively work to minimise and address bias. Incorporate ethical considerations into your AI strategy and continuously monitor and evaluate the AI's output for potential bias or ethical issues.These strategies can help mitigate the risks of using AI in workplace learning. However, each organisation's situation is unique, so it's important to continually assess and address risks in your specific context.Robin: In the past I’ve talked about how AI means that humans need to focus on the 3 things that AI can't do, Create, Collaborate and Change. What are your thoughts on this?ChatGPT: You've highlighted a critical perspective on the interaction between humans and AI in the workplace, and particularly in learning and development. AI technology has made significant strides, but there remain areas where humans outperform any existing AI. Let's unpack the three Cs you've mentioned:Create: While AI can generate content, solve problems within a specified context, and even mimic some forms of creativity, it fundamentally lacks the ability to truly innovate or think outside of the box. Human creativity, which involves the generation of new ideas, unique insights, and novel solutions, remains unchallenged. In learning and development, this creativity plays a crucial role in designing engaging and effective learning experiences.Collaborate: AI can facilitate collaboration (for example, by coordinating schedules or organising tasks), but it cannot truly collaborate the way humans can. Human collaboration involves complex social interactions, empathetic understanding, negotiation, and the ability to build on each other's ideas in dynamic, unpredictable ways. Especially in a learning context, this ability to collaborate and learn from each other is a deeply human skill that AI cannot replicate.Change: AI can adapt to new data within a predefined framework, but it doesn't have the capacity for the kind of flexible, broad-spectrum change and adaptability that humans possess. Humans can change their beliefs, assumptions, behaviors, and strategies based on new experiences or insights, and this ability is key to learning and development.In the context of learning while working, humans should leverage AI for what it does best - managing large amounts of data, providing personalised content, offering on-demand support, and automating routine tasks. Meanwhile, human efforts can focus on these irreplaceable areas of creativity, collaboration, and change, which are at the heart of effective learning and development. This combination of AI's capabilities and the unique human skills can lead to a powerful, holistic approach to workplace learning.Robin: Now as the wrap questions what your greatest piece of advice about using ChatGPT is for learning while working?ChatGPT: When it comes to using ChatGPT or any AI in the learning while working context, the most important piece of advice I'd give is this: View AI as a tool that augments and enhances human-led learning, not as a replacement for it.AI tools like ChatGPT can offer great advantages in terms of personalising learning, providing on-demand support, and automating routine tasks. But they are not a silver bullet. The effectiveness of AI in learning and development depends greatly on how it's integrated into your broader L&D strategy.Here are a few key points to consider:Learner-Centric Approach: Focus on the learner. AI offers exciting possibilities, but ultimately, the goal is to create a better, more effective, more engaging learning experience for your employees. So always consider how the use of AI will benefit the learner.Blend with Human Interaction: Balance the use of AI with opportunities for human interaction and guidance. While AI can deliver content and personalise learning, it can't replace the mentorship, social learning, and human touch that are also crucial for effective learning.Ongoing Evaluation: Continually evaluate and adjust your approach. AI is a rapidly evolving field, so it's important to stay updated with new developments and be ready to adapt your strategies. Regularly solicit feedback from learners and use it to improve your AI-enhanced learning experiences.Training & Support: Provide training and support to help employees use AI tools effectively. Not everyone may be comfortable with technology, so it's important to help them understand how to use AI tools and how they can benefit from them.By keeping these principles in mind, organisations can leverage the power of AI to transform workplace learning, while still maintaining a human-centric approach that values and nurtures the unique capabilities of each individual learner.