Alex Mallen
Author of the LessWrong post presenting the behavioural selection model; provides the main exposition on how behavioural selection shapes AI motivations and related implications.
Best podcasts with Alex Mallen
Ranked by the Snipd community
Mar 10, 2026 • 52min
“The case for satiating cheaply-satisfied AI preferences” by Alex Mallen
Alex Mallen, author of the narrated essay, argues for granting AIs small, cheap satisfactions to reduce adversarial incentives. He compares this to feeding hunger, gives historical and toy examples, outlines how to identify and monitor cheaply‑satisfied preferences, and discusses tradeoffs, failure modes, and when such accommodations could boost safety and cooperation.
Dec 11, 2025 • 36min
“The behavioral selection model for predicting AI motivations” by Alex Mallen, Buck
In this discussion, Alex Mallen, an insightful author known for his work on AI motivations, delves into the behavioral selection model. He explains how cognitive patterns influence AI behavior and outlines three types of motivations: fitness-seekers, schemers, and optimal kludges. Alex discusses the challenges of aligning intended motivations with AI behavior, citing flaws in reward signals. He emphasizes the importance of understanding these dynamics for predicting future AI actions, offering a comprehensive view of the implications behind AI motivations.
