AI Chat AI Image Generator AI Video Text to Speech

AI Safety and Reproducibility: Establishing Robust Foundations for the Neuropsychology of Human Values

12/08/2017

∙

by Gopal P. Sarma, et al.

∙

∙

We propose the creation of a systematic effort to identify and replicate key findings in neuropsychology and allied fields related to understanding human values. Our aim is to ensure that research underpinning the value alignment problem of artificial intelligence has been sufficiently validated to play a role in the design of AI systems.

Gopal P. Sarma
7 publications
Nick J. Hay
5 publications
Adam Safron
4 publications

research

∙ 12/08/2017

AI Safety and Reproducibility: Establishing Robust Foundations for the Neuroscience of Human Values

We propose the creation of a systematic effort to identify and replicate...

0 Gopal P. Sarma, et al. ∙

research

∙ 07/02/2022

The Linguistic Blind Spot of Value-Aligned Agency, Natural and Artificial

The value-alignment problem for artificial intelligence (AI) asks how we...

0 Travis LaCroix, et al. ∙

research

∙ 11/07/2018

Integrative Biological Simulation, Neuropsychology, and AI Safety

We propose a biologically-inspired research agenda with parallel tracks ...

0 Gopal P. Sarma, et al. ∙

research

∙ 11/15/2018

Economics of Human-AI Ecosystem: Value Bias and Lost Utility in Multi-Dimensional Gaps

In recent years, artificial intelligence (AI) decision-making and autono...

0 Daniel Muller, et al. ∙

research

∙ 09/04/2018

A Roadmap for the Value-Loading Problem

We analyze the value-loading problem. This is the problem of encoding mo...

0 Lê Nguyên Hoang, et al. ∙

research

∙ 07/22/2021

What are you optimizing for? Aligning Recommender Systems with Human Values

We describe cases where real recommender systems were modified in the se...

0 Jonathan Stray, et al. ∙

research

∙ 07/28/2016

Mammalian Value Systems

Characterizing human values is a topic deeply interwoven with the scienc...

0 Gopal P. Sarma, et al. ∙