The Behavioral Data Science Podcast

"Explainable AI", aka XAI, refers to a suite of techniques to help AI system developers and AI system users understand why inputs to the system resulted in the observed outputs. Industries such as healthcare, education, and finance require that any system using mathematical models or algorithms to influence the lives of others is transparent and explainable. In this episode, Jake and Dav...

Prompt engineering involves a lot more than simply getting smarter with how you structure the prompts you enter in an LLM browser interface. Furthermore, a growing body of peer-reviewed research provides us with best practices to improve the accuracy and reliability of LLM outputs for the specific tasks we build systems around. In this episode, Jake and David review evidence-based best practices f...

Lots of people like to talk about the importance of prompts, context, and what is sent to an LLM. Few discuss the even more important aspect of an LLM-driven system in evaluating its output. In this episode, we discuss traditional and modern metrics used to evaluate LLM outputs. And, we review the common frameworks for obtaining that feedback. Though evals are a lot of work (and easy to do poorly)...

Jake and David chat about best practices and considerations for those building and using AI systems that leverage LLMs.

Jake and David chat about types of GenAI, and specifically how LLMs work—from input text or audio through the output you read.

Jake and I chat about current hot topics in the LLM space and what we would (and would not) trust an LLM with.

Jake and I chat about a forthcoming book chapter titled, "Welcome to the Era of Experience" by David Silver and Richard Sutton (link below). This—naturally—led other topics to surface, such as companies staffed entirely by AI agents (which turned out as well as that sounds); superintelligence (we might be legally required to reference this during the 2025 AI hype cycle); and how practica...

In this episode, we chat with Dr. Beth Garrison about her journey in behavior analysis, what led her to pursue a PhD in artificial intelligence, and her thoughts on where this is all headed. Links to the papers Dr. Garrison references: Exploring Engagement Opportunities for Autistic Children: Using AAC as a Controller in a Wizard-of-Oz Coloring Game: https://doi.org/10.1145/3701193 Understanding t...

In this episode, David talks about the dataset he's been collecting on his own, daily behavior over the last 15 years; and, how behavior science + data science let him do neat things with it.

Jake talks about his backyard science project where he used computer vision to detect squirrels in his backyard.

In this episode, we dive into some basics around unsupervised machine learning and how behavior analysts might use it in their work.

Episode 010: Guest Chat with Zach Morford

Episode 009: What does it take to go end-to-end with an AI application? Part III - The Deployment Lifecycle

In this episode, we discuss the end-to-end pipeline when creating a model.

In this episode, we talk about the many components of data engineering and parallel work data scientists get into as data moves from its data collection source to being ready for modeling.

In this episode, we discuss common barriers and solutions for bridging the research-to-practice gap in behavioral data science. We also talk about many of the ways that data science or AI research differs from behavior science research in terms of practitioners' ability to integrate findings quickly into practice.

Episode 005: Do LLMs display Verbal Behavior?

Episode 004: Vector Embeddings: What, how, and why for BSci

Episode 003: Getting into data science with a behavioral science background.

In this episode, Jake and David discuss how one might even define what it means for something to exist at the intersection of behavior science and data science. We also talk about the different roles on data science teams and applied behavior analysis teams. And we talk about how long it might be until AI systems are better at the functional analysis of behavior than humans.

Welcome to the Behavioral Data Science podcast. A podcast for those interested in what's going on at the intersection of behavior science and data science.