Generation AI

In this episode, we welcome Kara Peterson and Rich DiBona, founders of descrybe.ai, a justice tech startup aimed at democratizing access to the law. Kara is a marketing and business development leader with a strong emerging following in the Legal AI space and is being hosted by the National Law Review as one of the hottest legal tech companies in 2025. Rich is the tech side of descrybe.ai and comes from a software engineering background, where he worked on architecture and scaling with large amounts of data. Kara and Rich discuss with us the most pressing ideas in the legal AI space, including the trustworthiness of answers and how observability and explainability are so important in legal AI use cases. Our guests also share their vision of how generative AI can enable social change by quickly identifying precedence in cases, which can save operational and administrative costs to people employing these legal services. Will AI create a more equitable future for the legal space? Join the podcast and find out!

Ayush Garg is the founder of AnswerThis.io. He is passionate about reimagining how science is conducted. His journey started with making tools like pygetpapers and docanalysis that scaled to over 50,000 researchers and has since evolved into building AnswerThis. Ayush discusses his approach to building retrieval systems over the years, addressing issues like observability and citations. He dictates his future LLM wishlist, and we have a blast with our rapid-fire questions. We think you will enjoy Ayush's experience in AI development.

This month, we sat down with Tobias Lunt, another amazing presenter from this year’s Data Council Lightning Talks. Tobias is using LLMs at Development Data Lab to analyze, expose, and combat gender inequality and understand the impact of societal norms. He has a unique perspective on how academia and the public sector view data science tooling in relation to the commercial landscape. Tobias puts into perspective the “big” nature of data in his line of work and talks about the meteoric rise in LLM accuracy that we are seeing in the space but also cautions us about the false artifacts that can still be present in RAG systems and with manually defined data sets. We hope you enjoy finding out more about what Tobias and his team are up to.

This month, we chat with Amber Roberts, Senior Technical PMM from Arize AI. We met Amber this year at the Data Council conference, where we learned a lot about the concepts around LLM Observability during her great presentation. We wanted to dive a bit deeper on the podcast. Amber chats with us about the foundational pillars of LLM observability including traces and spans and RAG/fine-tuning, the role of drift in LLMs, and how you can evaluate attributes like fairness and rudeness. Learn more about all the great projects and classes that Amber is leading and hear more about the Data Council conference. Links: Arize Community Arize Phoenix HomePage Phoenix Github

This month, we tried something different and sat down with my co-host, Ofer Mendelevitch, to get his hot takes on topics like vector databases, agents, and fine-tuning. Ofer has a storied career in Big Data, machine learning, and AI. An in-demand speaker and community champion, Ofer is active in the ecosystem as the Head of Developer Advocacy @ Vectara. Don't miss this chance to get to know Ofer and pay witness to his unique AI forecasts.

Ram Sriharsha, VP of Engineering at Pinecone, discusses vector databases and LLMs, including Hybrid Search and both sparse and dense retrieval. He introduces the concept of retrieval augmented generation (RAG) to enhance language models with knowledge from vector databases. The podcast explores the importance of search relevancy in AI chatbot development and the impact of longer sequence windows in language models. Challenges of cloud native platforms and the future possibilities of machine learning models are also discussed.

For this episode, we sit down with Lolpop creator and head of field operations at Voltron Data, Jordan Volz. Jordan is a known force in data and ML space and has advised countless organizations on how to get more models into production. With his new open-source project, Jordan aims to bring many of the cemented software development strategies to data science work, ensuring that data science outputs are reliable in production. Jordan chats with us about the rise of LLMs, the areas where traditional machine learning will still likely dominate, and what data scientists should have front of mind.

In this episode, we welcome Bob van Luijt, a technology entrepreneur, technologist, and new media artist from the Netherlands. He is the co-founder and CEO of Weaviate, an open-source vector database, and the chairman of the Creative Software Foundation. Bob is an active force in the AI and Vector Database community and has a front seat to the core shifts in the AI landscape. Bob skips the tea and goes straight to soup with piping hot takes on Hybrid Search, vector database abundance, and generative feedback loops. This conversation serves as a quintessential primer for understanding vector embeddings and what they are used for.

Tri Dao is known for his groundbreaking work on Flash Attention at Stanford, enabling a fast and efficient implementation of the Attention mechanism in Transformers, opening up possibilities for much longer sequence length in GPT-4, Claude Anthropic as well as in images, video and audio. We sat down with Tri Dao to discuss the impact of his pioneering work on software/hardware co-design and some of the new innovation that's coming in the world of transformers and generative AI.

Sean and Ofer sit down with Race Capital's Alfred Chuang, a Silicon Valley luminary and prolific storyteller. Alfred Chuang is a general partner at Race Capital and is also known for being the co-founder and CEO of BEA Systems, Alfred led BEA Systems to its acquisition by Oracle in 2008 for $8.6 billion. Alfred chats about his excitement around generative AI and offers predictions as to where the market is heading, including how you can better take care of your houseplants. Alfred's experience in transformational moments in tech provides a lively discussion on how AI will transform every aspect of our lives.