Dr. Phelps will be giving a talk ‘A Behavioral Economics Approach To AI Safety’ at the Annual Quant Insights Conference on 1st November.

He will discuss experiments into how large-language models behave in principal-agent conflicts, how they respond to changes in information asymmetry, and whether they can establish trust through reciprocity.

Book your free conference ticket here: lnkd.in/exgBeEs3

The talk is based on a working paper “Of Models and Tin Men: A Behavioural Economics Study of Principal-Agent Problems in AI Alignment using Large-Language Models”- link here: https://arxiv.org/abs/2307.11137.


No responses yet

Leave a Reply

Your email address will not be published. Required fields are marked *