Stories from the Hackery

Stories from the Hackery

Find out what it takes to start a career in software development, data analytics, data science, or UI/UX design from those who made the leap. Hear from musicians, veterans, single-moms, teachers, bartenders, postdocs, warehouse workers, and more - all graduates of Nashville Software School (NSS) - as they discuss their transition to tech and their capstone projects presented at Demo Day. Founded in 2012, NSS is a flourishing community of over one thousand alumni, active students, and a team of dedicated instructors all working together to grow and learn their craft. As a non-profit, NSS is committed to growing diversity in tech by creating opportunities for under-represented groups in these fields. Learn more at nashvillesoftwareschool.com.

  1. MAY 8

    Using LLMs Beyond the Chatbot | Stories From The Hackery

    As we continue to discuss generative AI on Nashville Software School’s podcast, Stories from the Hackery, Founder and CEO John Wark and lead Data instructor Michael Holloway, dive into various techniques for leveraging large language models (LLMs) like generative AI. They explore the potential of using hosted public LLMs via chatbot interfaces and discuss strategies for embedding LLMs into applications. One such technique discussed is the use of a prompt engineering, which involves wrapping the LLM API to tailor user prompts for more effective responses. They also discuss more advanced techniques like retrieval-augmented generation (RAG), which involves using external data to tailor LLM responses further. This approach helps mitigate challenges like hallucination and ensures contextually relevant responses. Additionally, they touch on fine-tuning LLMs for specific applications, which requires more computational resources and domain expertise. John and Michael highlight the importance of having machine learning skills to implement these techniques effectively. While fine-tuning LLMs may require specialized skills and resources, the emergence of smaller LLMs makes certain applications more accessible. They also mention the potential of multi-agent models for deeper and more focused outputs, indicating an exciting direction for LLM applications. For more information on the evolving landscape of LLMs and the need for organizations to stay informed about these advancements to harness their full potential in this episode of Stories from the Hackery by Nashville Software School. START YOUR NSS JOURNEY To learn more about Nashville Software School and our upcoming programs, visit our website at https://NashvilleSoftwareSchool.com SUPPORT NSS Want to support NSS in our mission to teach adults skills needed for careers in tech? Visit our website to donate to the scholarship fund and learn about other volunteer opportunities! Nashss.com/Give CHAPTERS: 00:00 - Introduction 01:57 - Public Chat Bot Usage 02:47 - Prompt Engineering 03:21 - Retrieval Augmented Generation (RAG) 3:57 - Fine Tuning of Models 04:37 - Technical Implementation 05:10 - Product Engineering and Its Role 08:17 - Implementing Prompt and Product Engineering 10:15 - Utilizing External Context with RAG 11:20 - Responsible AI Considerations 16:57 - Overcoming Challenges and Limitations 23:53 - Future Trends and Considerations 29:48 - Prompt and product engineering techniques

    57 min
  2. APR 24

    How is Generative AI Impacting Data Analytics and Data Science? | Stories from the Hackery

    In this episode of Stories from the Hackery, Founder and CEO of Nashville Software School, John Wark, sits down with lead analytics instructor, Michael Holloway, to provide insights into the impact of generative AI tools like ChatGPT on data analytics and data science. They highlight the importance of human oversight and contextual understanding in leveraging these tools effectively as well as strategies for adapting programs at Nashville Software School to prepare students for evolving roles in data analytics and data science are discussed, emphasizing the need for continuous learning and skill development. START YOUR NSS JOURNEY To learn more about Nashville Software School and our upcoming programs, visit our website at https://NashvilleSoftwareSchool.com SUPPORT NSS Want to support NSS in our mission to teach adults skills needed for careers in tech? Visit our website to donate to the scholarship fund and learn about other volunteer opportunities! https://Nashss.com/Give CHAPTERS: 00:00 - Introduction. 03:10 - An overview of data analytics and data science. 04:30 - The evolution and impact of generative AI tools like ChatGPT and their role in supporting data analytics and data science tasks. 05:33 - Similarities and differences between software development and data analytics/data science are explored, focusing on how generative AI tools transform learning and work processes. 06:31 - Similarities in using generative AI tools for coding tasks and the importance of understanding contextual knowledge and problem domains. 08:12 - Key differences between software development and data analytics/data science, such as exploratory nature and iterative problem-solving approaches, are highlighted. 10:18 - The iterative exploration process in data analytics is discussed, emphasizing the need for planning, design, and contextual understanding of the data. 12:10 - Limitations of generative AI tools like ChatGPT in reasoning and understanding complex data contexts are explained. 13:05 - Capabilities and limitations of generative AI tools, emphasizing their dependence on training data and human validation. 17:42 - The importance of human oversight in using generative AI tools. 22:58 - Domain expertise in data analytics and data science tasks, emphasizing the limitations of generative AI tools. 24:48 Training strategies at NSS to prepare students for evolving roles in data analytics and data science. 46:08 - Strategies for adapting training content to incorporate skills relevant to generative AI tools. 01:04:2 - Closing.

    1h 5m
  3. MAR 12

    The Developers Ally: GenAI's True Role In Software Creation - Stories From The Hackery Podcast

    Nashville Software School Founder and CEO John Wark sits down with Full-time Web Development Lead Instructor, Steve Brownlee, to discuss Steve’s research in how generative AI can be a helpful tool the popularity of LLMs continue to grow in software development. Learn more about Nashville Software School and our upcoming programs when you visit our website: https://NashvilleSoftwareSchool.com 0:00 Intro 1:53: Generative AI is creating a new set of skills that developers need to learn 5:29 How NSS grads were using generative AI in mid-2023 9:30 The generative AI hype cycle & NSS’s exploration 14:05 How have NSS’s students learned to use generative AI as a learning assistant 20:04 Deepening our understanding of generative AI 24:50 Steve Brownlee’s exploration of generative AI for developers 31:40 Can these tools handle system level tasks? 42:52 Exploration with GitHub Copilot 49:33 Grading ChatGPT, Claude, and GitHub Copilot models 51:10 Takeaways: How we plan to incorporate generative AI and prompt engineering into our Web Developer program 1:01:25 Final Thoughts Resources References in this podcast: Steve Brownlee’s blog post: https://www.stevebrownlee.com/genai-stole-my-work/ Chat GPT: https://chat.openai.com/ Claude: https://claude.ai/login?returnTo=%2F Copilot: https://github.com/features/copilot Language References found in the podcast: GenAI = Generative AI. Refers to artificial intelligence systems that have the capability to generate new content, such as images, text, audio, or even video, that is similar to, or inspired by, the data they were trained on. These systems are designed to learn the underlying patterns and structures within the data and then generate novel outputs based on that understanding. LLMs = Large Language Models. Refers to a type of artificial intelligence (AI) model that has been trained on vast amounts of text data in order to understand and generate human-like language. These models, such as OpenAI's GPT (Generative Pre-trained Transformer) series, are designed to process and generate text in a wide range of contexts, tasks, and languages. Foundation Model = Foundation models use self-supervised learning to create labels from input data. This means no one has instructed or trained the model with labeled training data sets. This feature separates LLMs from previous ML architectures, which use supervised or unsupervised learning. Emergent Behavior = Refers to actions or patterns that weren't explicitly programmed into an AI system but developed as a natural outcome of its complexity and interactions. Imagine a colony of ants. No single ant has the blueprint for the colony's intricate behavior. Producer & Editor: Jessica Grande

    1h 5m

Ratings & Reviews

5
out of 5
4 Ratings

About

Find out what it takes to start a career in software development, data analytics, data science, or UI/UX design from those who made the leap. Hear from musicians, veterans, single-moms, teachers, bartenders, postdocs, warehouse workers, and more - all graduates of Nashville Software School (NSS) - as they discuss their transition to tech and their capstone projects presented at Demo Day. Founded in 2012, NSS is a flourishing community of over one thousand alumni, active students, and a team of dedicated instructors all working together to grow and learn their craft. As a non-profit, NSS is committed to growing diversity in tech by creating opportunities for under-represented groups in these fields. Learn more at nashvillesoftwareschool.com.

More From NashviIIe Software School

To listen to explicit episodes, sign in.

Stay up to date with this show

Sign in or sign up to follow shows, save episodes, and get the latest updates.

Select a country or region

Africa, Middle East, and India

Asia Pacific

Europe

Latin America and the Caribbean

The United States and Canada