Jun 9
Is RAG Dead? Lessons from Building AI for Tax Law with Alex Bowcut - #769
As context windows grow into the millions of tokens, many AI practitioners are questioning whether retrieval-augmented generation (RAG) is still necessary. If modern models can ingest entire libraries of documents, why bother with retrieval at all? In this episode, Alex Bowcut, H ... Show More
51m 32s
May 21
Relational Foundation Models for Enterprise Data with Jure Leskovec - #768
In this episode, Jure Leskovec, co-founder and chief scientist at Kumo and professor of computer science at Stanford, joins us to explore two fronts of his work: AI for science and relational deep learning. We begin with AI Virtual Cell, a multiscale effort to learn data-driven r ... Show More
1h 6m
May 7
How to Find the Agent Failures Your Evals Miss with Scott Clark - #767
In this episode, Scott Clark, co-founder and CEO of Distributional, joins us to explore how teams can reliably operate and improve complex LLM systems and agents in production. Scott introduces a Maslow’s hierarchy of observability: telemetry for logging, monitoring for known sig ... Show More
53m 19s
Apr 2023
The Power of Graph Neural Networks: Understanding the Future of AI - Part 2/2 (Ep.224)
<p>In this episode of our podcast, we dive deep into the fascinating world of Graph Neural Networks.</p>
<p>First, we explore Hierarchical Networks, which allow for the efficient representation and analysis of complex graph structures by breaking them down into smaller, more mana ... Show More
35m 32s
Jun 2024
Cameron J. Buckner, "From Deep Learning to Rational Machines" (Oxford UP, 2023)
Artificial intelligence started with programmed computers, where programmers would manually program human expert knowledge into the systems. In sharp contrast, today's artificial neural networks – deep learning – are able to learn from experience, and perform at human-like levels ... Show More
1h 11m
Mar 2021
The Theory of a Thousand Brains
<p>In this episode, we talk with Jeff Hawkins—an entrepreneur and scientist, known for inventing some of the earliest handheld computers, the Palm and the Treo, who then turned his career to neuroscience and founded the Redwood Center for Theoretical Neuroscience in 2002 and Nume ... Show More
39m 36s
Today we’re joined by Sophia Sanborn, a postdoctoral scholar at the University of California, Santa Barbara. In our conversation with Sophia, we explore the concept of universality between neural representations and deep neural networks, and how these principles of efficiency provide an ability to find consistent features across networks and tasks. We also d ... Show More
<p><span style= "color: #224422; font-family: 'Lucida Bright', Georgia, serif; font-size: medium;"> My guest this week is Anh Nguyen, a PhD student at the University of Wyoming working in the </span><a style= "font-family: 'Lucida Bright', Georgia, serif; font-size: medium;" href ... Show More
