Vanishing Gradients

Episode 40: What Every LLM Developer Needs to Know About GPUs

December 24th, 2024  |  Season 1  |  1 hr 43 mins

ai, data science, llms, machine learning

Hugo speaks with Charles Frye, Developer Advocate at Modal and someone who really knows GPUs inside and out. If you’re a data scientist, machine learning engineer, AI researcher, or just someone trying to make sense of hardware for LLMs and AI workflows, this episode is for you.

Charles and Hugo dive into the practical side of GPUs—from running inference on large models, to fine-tuning and even training from scratch.

Episode 39: From Models to Products: Bridging Research and Practice in Generative AI at Google Labs

November 26th, 2024  |  Season 1  |  1 hr 43 mins

ai, data science, llms, machine learning

From building rockets at SpaceX to advancing generative AI at Google Labs, Ravin Kumar has carved a unique path through the world of technology. In this episode, we explore how to build scalable, reliable AI systems, the skills needed to work across the AI/ML pipeline, and the real-world impact of tools like open-weight models such as Gemma. Ravin also shares insights into designing AI tools like Notebook LM with the user journey at the forefront.

Episode 38: The Art of Freelance AI Consulting and Products: Data, Dollars, and Deliverables

November 5th, 2024  |  Season 1  |  1 hr 23 mins

consulting, data science, genai, llms, machine learning

Hugo speaks with Jason Liu, an independent AI consultant with experience at Meta and Stitch Fix. At Stitch Fix, Jason developed impactful AI systems, like a $50 million product similarity search and the widely adopted Flight recommendation framework. Now, he helps startups and enterprises design and deploy production-level AI applications, with a focus on retrieval-augmented generation (RAG) and scalable solutions.

Episode 37: Prompt Engineering, Security in Generative AI, and the Future of AI Research Part 2

October 8th, 2024  |  Season 1  |  50 mins 36 secs

data science, genai, llms, machine learning, nlp, prompt engineering

Hugo speaks with three leading figures from the world of AI research: Sander Schulhoff, a recent University of Maryland graduate and lead contributor to the Learn Prompting initiative; Philip Resnik, professor at the University of Maryland, known for his pioneering work in computational linguistics; and Dennis Peskoff, a researcher from Princeton specializing in prompt engineering and its applications in the social sciences.

Episode 36: Prompt Engineering, Security in Generative AI, and the Future of AI Research Part 1

September 30th, 2024  |  Season 1  |  1 hr 3 mins

data science, genai, llms, machine learning, nlp, prompt engineering

Hugo speaks with three leading figures from the world of AI research: Sander Schulhoff, a recent University of Maryland graduate and lead contributor to the Learn Prompting initiative; Philip Resnik, professor at the University of Maryland, known for his pioneering work in computational linguistics; and Dennis Peskoff, a researcher from Princeton specializing in prompt engineering and its applications in the social sciences.

Episode 35: Open Science at NASA -- Measuring Impact and the Future of AI

September 19th, 2024  |  Season 1  |  58 mins 13 secs

data science, genai, llms, machine learning

Hugo speaks with Dr. Chelle Gentemann, Open Science Program Scientist for NASA’s Office of the Chief Science Data Officer, about NASA’s ambitious efforts to integrate AI across the research lifecycle. In this episode, we’ll dive deeper into how AI is transforming NASA’s approach to science, making data more accessible and advancing open science practices.

Episode 34: The AI Revolution Will Not Be Monopolized

August 22nd, 2024  |  Season 1  |  1 hr 42 mins

data science, genai, llms, machine learning, nlp

Hugo speaks with Ines Montani and Matthew Honnibal, the creators of spaCy and founders of Explosion AI. Collectively, they've had a huge impact on the fields of industrial natural language processing (NLP), ML, and AI through their widely-used open-source library spaCy and their innovative annotation tool Prodigy.

Episode 32: Building Reliable and Robust ML/AI Pipelines

July 27th, 2024  |  Season 1  |  1 hr 15 mins

data science, genai, llms, machine learning

Hugo speaks with Shreya Shankar, a researcher at UC Berkeley focusing on data management systems with a human-centered approach. Shreya's work is at the cutting edge of human-computer interaction (HCI) and AI, particularly in the realm of large language models (LLMs). Her impressive background includes being the first ML engineer at Viaduct, doing research engineering at Google Brain, and software engineering at Facebook.

Episode 31: Rethinking Data Science, Machine Learning, and AI

July 9th, 2024  |  Season 1  |  1 hr 36 mins

data science, genai, llms, machine learning

Hugo speaks with Vincent Warmerdam, a senior data professional and machine learning engineer at :probabl, the exclusive brand operator of scikit-learn. Vincent is known for challenging common assumptions and exploring innovative approaches in data science and machine learning.

Episode 28: Beyond Supervised Learning: The Rise of In-Context Learning with LLMs

June 10th, 2024  |  Season 1  |  1 hr 5 mins

data science, genai, llms, machine learning

Hugo speaks with Alan Nichol, co-founder and CTO of Rasa, where they build software to enable developers to create enterprise-grade conversational AI and chatbot systems across industries like telcos, healthcare, fintech, and government.