Browsing by Author "Pedersen M"

Now showing 1 - 3 of 3

A Hormetic Approach to the Value-Loading Problem: Preventing the Paperclip Apocalypse
(Springer Nature Singapore Pte Ltd, 2025-10-06) Henry NIN; Pedersen M; Williams M; Martin JLB; Donkin L
The value-loading problem is a major obstacle to creating Artificial Intelligence (AI) systems that align with human values and preferences. Central to this problem is the establishment of safe limits for repeatable AI behaviors. We introduce hormetic alignment, a paradigm to regulate the behavioral patterns of AI, grounded in the concept of hormesis, where low frequencies or repetitions of a behavior have beneficial effects, while high frequencies or repetitions are harmful. By modeling behaviors as allostatic opponent processes, we can use either Behavioral Frequency Response Analysis (BFRA) or Behavioral Count Response Analysis (BCRA) to quantify the safe and optimal limits of repeatable behaviors. We demonstrate how hormetic alignment solves the ‘paperclip maximizer’ scenario, a thought experiment where an unregulated AI tasked with making paperclips could end up converting all matter in the universe into paperclips. Our approach may be used to help create an evolving database of ‘values’ based on the hedonic calculus of repeatable behaviors with decreasing marginal utility. Hormetic alignment offers a principled solution to the value-loading problem for repeatable behaviors, augmenting current techniques by adding temporal constraints that reflect the diminishing returns of repeated actions. It further supports weak-to-strong generalization – using weaker models to supervise stronger ones – by providing a scalable value system that enables AI to learn and respect safe behavioral bounds. This paradigm opens new research avenues for developing computational value systems that govern not only single actions but the frequency and count of repeatable behaviors.
Behavioral Posology: A Novel Paradigm for Modeling the Healthy Limits of Behaviors
(John Wiley and Sons, Inc., 2023-09-01) Henry N; Pedersen M; Williams M; Donkin L
One of the challenges faced by behavioral scientists is the lack of modeling methodologies for accurately determining when a behavior becomes problematic. The authors propose “behavioral posology” as a novel modeling paradigm for quantifying the healthy limits of behaviors through the concept of behavioral dose. As an example of this paradigm, a pharmacokinetic/pharmacodynamic model of a hypothetical digital behavior is presented, based on opponent process theory. The generic model can be adapted to simulate Solomon and Corbit's model of affective dynamics from 1974, and the model predicts features of addiction such as hedonic allostasis, withdrawal, and apparent tolerance. A behavioral frequency response analysis (BFRA) of the model demonstrates how behavior repetition may result in a hormetic dose–response relationship that depends on the frequency of the behavior. The model can be experimentally validated using Ecological Momentary Assessment, allowing researchers to hypothesize, model, and test causal mechanisms for behavioral addictions. The potential for behavioral posology to be applied as a clinical support tool in psychological medicine is discussed, as this modeling framework may help to detect and limit behaviors being performed too frequently based on factors such as the person's moral beliefs.
mHealth Technologies for Managing Problematic Pornography Use: Content Analysis.
(JMIR Publications, 2022-10-13) Henry N; Donkin L; Williams M; Pedersen M
Background: Several mobile apps are currently available that purportedly help with managing pornography addiction. However, the utility of these apps is unclear, given the lack of literature on the effectiveness of mobile health solutions for problematic pornography use. Little is also known about the content, structure, and features of these apps. Objective: This study aims to characterize the purpose, content, and popularity of mobile apps that claim to manage pornography addiction. Methods: The phrase “pornography addiction” was entered as a search term in the app stores of the two major mobile phone platforms (Android and iOS). App features were categorized according to a coding scheme that contained 16 categories. Apps were included in the analysis if they were described as helpful for reducing pornography use, and data were extracted from the store descriptions of the apps. Metrics such as number of user ratings, mean rating score, and number of installations were analyzed on a per-feature basis. Results: In total, 170 apps from both app stores met the inclusion criteria. The five most common and popular features, both in terms of number of apps with each feature and minimum possible number of installations, were the ability to track the time since last relapse (apps with feature=72/170, 42.4%; minimum possible number of installations=6,388,000), tutorials and coaching (apps with feature=63/170, 37.1%; minimum possible number of installations=9,286,505), access to accountability partners or communities (apps with feature=51/170, 30%; minimum possible number of installations=5,544,500), content blocking or content monitoring (apps with feature=46/170, 27.1%; minimum possible number of installations=17,883,000), and a reward system for progress (apps with feature=34/170, 20%; minimum possible number of installations=4,425,300). Of these features, content-blocking apps had the highest minimum possible number of installations. Content blocking was also the most detected feature combination in a combinatorial analysis (with 28 apps having only this feature), but it also had the lowest mean consumer satisfaction rating (4.04) and second-lowest median rating (4.00) out of 5 stars. None of the apps reviewed contained references to literature that provided direct evidence for the app’s efficacy or safety. Conclusions: There are several apps with the potential to provide low- or zero-cost real-time interventions for people struggling to manage problematic pornography use. Popular app features include blockers of pornographic content, behavior monitoring, and tutorials that instruct users how to eliminate pornography use. However, there is currently no empirical evidence to support the effectiveness and safety of these apps. Further research is required to be able to provide recommendations about which apps (and app features) are safe for public consumption.