Practical AI
Practical AI LLC
Making artificial intelligence practical, productive & accessible to everyone. Practical AI is a show in which technology professionals, business people, students, enthusiasts, and expert guests engage in lively discussions about Artificial Intelligence and related topics (Machine Learning, Deep Learning, Neural Networks, GANs, MLOps, AIOps, LLMs & more).
The focus is on productive implementations and real-world scenarios that are accessible to everyone. If you want to keep up with the latest advances in AI, while keeping one foot in the real world, then this is the show for you!
The focus is on productive implementations and real-world scenarios that are accessible to everyone. If you want to keep up with the latest advances in AI, while keeping one foot in the real world, then this is the show for you!
Episodes
Mentioned books
33 snips
Oct 15, 2024 • 58min
Practical workflow orchestration
Adam Azzam, a principal product manager at Prefect, and Michael Greenwich, CEO of WorkOS, dive into the complexities of workflow orchestration in AI applications. They discuss how Prefect’s open-source library tackles the pains of managing workflows and introduces tools like Marvin for real-time support. The conversation highlights the importance of error management, visibility in pipelines, and the seamless integration of enterprise features for faster product development, showcasing innovative solutions for modern engineers.
5 snips
Oct 9, 2024 • 57min
Towards high-quality (maybe synthetic) datasets
David Berenstein, a developer advocate engineer at Hugging Face, and Ben Burtenshaw, a machine learning engineer at Argilla, dive into the crucial realm of data quality in AI. They discuss how collaboration between domain experts and data scientists significantly enhances model efficacy. The conversation covers innovative strategies for generating synthetic datasets, utilizing AI for labeling, and maintaining privacy. The duo also shares insights on the importance of effective feedback loops and multimodal data integration for refining AI training.
22 snips
Oct 3, 2024 • 1h 2min
Understanding what's possible, doable & scalable
Mike Lewis, an AI architect from Cincinnati, shares his insights on leveraging LLM and GenAI applications for real enterprise value. He tackles the prevalent AI disillusionment, emphasizing the importance of creativity and understanding client needs. The discussion touches on developing tailored AI solutions, unlocking operational efficiencies, and recognizing AI's broader societal impact. Mike also advocates for empowering non-technical workers with AI knowledge, and highlights the innovative application of AI in enhancing sleep quality with cutting-edge technology.
60 snips
Sep 25, 2024 • 55min
GraphRAG (beyond the hype)
Prashanth Rao, an AI engineer at Kuzu known for his expertise in graph databases, joins the discussion to unravel the complexities of GraphRAG. He delves into the practical applications of graph databases, particularly in healthcare and finance. The conversation highlights how integrating graph and vector databases enhances information retrieval. Prashanth also shares insights on the evolution of retrieval augmented generation, focusing on how advanced techniques can improve the accuracy of AI models.
26 snips
Sep 17, 2024 • 50min
Pausing to think about scikit-learn & OpenAI o1
Discover how scikit-learn's recent seed funding may reshape the data science landscape. Uncover the intrigue behind OpenAI's new model, which pauses to ponder complex tasks. The discussion dives into the vital role of core data science amid AI hype and the challenges of navigating AI’s rapid evolution. Explore its marketing strategies and user interface pitfalls, while also examining AI’s applications in physics research. Plus, there's a passionate plea for the value of open-source tools and community collaboration in advancing knowledge.
41 snips
Sep 11, 2024 • 52min
Cybersecurity in the GenAI age
Dinis Cruz, Founder of The Cyber Boardroom and OWASP contributor, joins the conversation to tackle cybersecurity in the era of generative AI. He discusses the importance of prioritizing security as developers face new threats. Dinis emphasizes OWASP's Top 10 for LLMs and the need for tailored security models to manage AI vulnerabilities. The dialogue reveals the duality of AI, balancing its benefits against risks, and highlights the challenges of misinformation generated by AI, advocating for transparency in addressing these issues.
31 snips
Sep 5, 2024 • 40min
AI is more than GenAI
The discussion dives into the fascinating evolution of artificial intelligence, charting its journey from statistical methods to generative models. Listeners learn how different AI methodologies are interrelated, emphasizing the importance of model training and data representation. This exploration provides a more comprehensive understanding of the AI landscape beyond just generative AI, highlighting the practical applications of these technologies.
10 snips
Aug 29, 2024 • 42min
Metrics Driven Development
Shahul Es, Co-founder of Ragas, discusses innovative approaches to evaluating LLM applications. He emphasizes the significance of Metrics Driven Development to systematically measure and enhance performance. The conversation contrasts assessing LLM applications with evaluating models, highlighting the need for tailored metrics and synthetic test data. Shahul shares insights on creating clear standards for better enterprise adoption, ensuring responsible and high-quality AI solutions. Tune in for an engaging deep dive into AI's evolving landscape!
28 snips
Aug 22, 2024 • 55min
Threat modeling LLM apps
Donato Capitella, Principal Security Consultant at WithSecure, specializes in threat modeling for AI applications. He discusses the critical need for threat modeling in the context of large language models (LLMs) and shares insights on vulnerabilities, such as prompt injection risks. Donato emphasizes the importance of validating outputs to maintain trustworthiness and explores innovative strategies for secure integration in AI systems. The conversation also touches on the exciting future of LLM technology and the role of ethical hackers in enhancing cybersecurity.
13 snips
Aug 14, 2024 • 46min
Only as good as the data
Explore the core idea that AI's effectiveness hinges on data quality. Dive into various data types crucial for training and fine-tuning models. Learn about selecting the right computer vision models and the role of labeling in supervised learning. The conversation also highlights the importance of effective test sets and benchmark data in machine learning. Plus, discover the EU AI Act and its global regulatory implications for AI applications, pointing to a future of increased governance and oversight.
