Send us a text Welcome to the cozy corner of the tech world where ones and zeros mingle with casual chit-chat. Datatopics Unplugged is your go-to spot for relaxed discussions around tech, news, data, and society. Dive into conversations that should flow as smoothly as your morning coffee (but don't), where industry insights meet laid-back banter. Whether you're a data aficionado or just someone curious about the digital age, pull up a chair, relax, and let's get into the heart of data, unplugged style! In this episode, host Murilo is joined by returning guest Paolo, Data Management Team Lead at dataroots, for a deep dive into the often-overlooked but rapidly evolving domain of unstructured data quality. Tune in for a field guide to navigating documents, images, and embeddings without losing your sanity. What we unpack: Data management basics: Metadata, ownership, and why Excel isn’t everything.Structured vs unstructured data: How the wild west of PDFs, images, and audio is redefining quality.Data quality challenges for LLMs: From apples and pears to rogue chatbots with “legally binding” hallucinations.Practical checks for document hygiene: Versioning, ownership, embedding similarity, and tagging strategies.Retrieval-Augmented Generation (RAG): When ChatGPT meets your HR policies and things get weird.Monitoring and governance: Building systems that flag rot before your chatbot gives out 2017 vacation rules.Tooling and gaps: Where open source is doing well—and where we’re still duct-taping workflows.Real-world inspirations: A look at how QuantumBlack (McKinsey) is tackling similar issues with their AI for DQ framework.

Send us a text Welcome to another engaging episode of Datatopics Unplugged, the podcast where tech and relaxation intersect. Today, we're excited to host two special guests, Paolo and Tim, who bring their unique perspectives to our cozy corner. Guests of Today Paolo: An enthusiast of fantasy and sci-fi reading, Paolo is on a personal mission to reduce his coffee consumption. He has a unique way of measuring his height, at 0.89 Sams tall. With over two and a half years of experience as a data engineer at dataroots, Paolo contributes a rich professional perspective. His hobbies extend to playing field hockey and a preference for the warmer summer season.Tim: Occasionally known as Dr. Dunkenstein, Tim brings a mix of humor and insight. He measures his height at 0.87 Sams tall. As the Head of Bizdev, he prefers to steer clear of grand titles, revealing his views on hierarchical structures and monarchies.Topics Biz Corner: Kyutai: We delve into France's answer to OpenAI with Paolo Leonard, exploring the implications and future of Kyutai: https://techcrunch.com/2023/11/17/kyutai-is-an-french-ai-research-lab-with-a-330-million-budget-that-will-make-everything-open-source/GPT-NL: A discussion led by Bart Smeets on the Netherlands' own open language model and its potential impact: https://www.computerweekly.com/news/366558412/Netherlands-starts-building-its-own-AI-language-modelTech Corner: Data Quality Insights: A blog post by Paolo on data quality vs. data validation. We'll explore when and why data quality is essential, and evaluate tools like dbt, soda, deequ, and great_expectations: https://dataroots.io/blog/state-of-data-quality-october-2023Soda Data Contracts: An overview of the newly released OSS Data Contract Engine by Soda. https://docs.soda.io/soda/data-contracts.htmlFood for Thought Corner: Hare - A 100-Year Programming Language: Bart starts a discussion on the ambition of Hare to remain relevant for a century: https://harelang.org/blog/2023-11-08-100-year-language/.Join us for this mix of expert insights and light-hearted moments. Whether you're deeply embedded in the tech world or just dipping your toes in, this episode promises to be both informative and entertaining!

And, yes. There is a voucher, go to dataroots.io and navigate to the shop (top right) and use voucher code murilos_bargain_blast for a 25EUR discount!