Unstructured

(somewhat) structured thoughts on (mostly) unstructured data

Category: LLMs

  • Emotions and AI

    I’ve been reading an absolutely fascinating book about how the brain works. Lisa Feldman Barrett’s “How Emotions Are Made: The Secret Life of the Brain” was published in 2017, so…

  • Automated Social Science

    While model estimation has made significant progress over the past two decades, model generation remains a relatively unexplored area. This new working paper by Ben Manning, Kehang Zhu, and John…

  • LLMs Behaving Badly

    Or goodly, depends who you ask! More evidence is trickling in that LLMs are just like us, humans. (Flawed. Biased. Complex. Interesting.) How so? Let’s start with this paper (cool…

  • Another Gino Experiment that Does Not Replicate (Synthetically)

    *This post is co-authored with Benjamin Manning, currently a PhD student at MIT in the IT group at Sloan* This post is a part of the series aimed at replicating papers…

  • Generative AI, Simulating Surveys, and the Future of Behavioral Science

    Survey-based research is about to change in a big way. As we can now tap into internet’s myriad voices with little effort (large language models!), we are seeing more and…

  • The Moral Virtue of Authenticity as a Large Language Model

    Behavioral science has faced some significant blows in 2023. One of the major reasons for the ongoing replication crisis in behavioral science is the considerable time and funding required to…

About