Concrete Problems in AI Safety, Revisited

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Raji, Inioluwa Deborah, Dobbe, Roel
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916100012244992
author Raji, Inioluwa Deborah
Dobbe, Roel
author_facet Raji, Inioluwa Deborah
Dobbe, Roel
contents As AI systems proliferate in society, the AI community is increasingly preoccupied with the concept of AI Safety, namely the prevention of failures due to accidents that arise from an unanticipated departure of a system's behavior from designer intent in AI deployment. We demonstrate through an analysis of real world cases of such incidents that although current vocabulary captures a range of the encountered issues of AI deployment, an expanded socio-technical framing will be required for a more complete understanding of how AI systems and implemented safety mechanisms fail and succeed in real life.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10899
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Concrete Problems in AI Safety, Revisited
Raji, Inioluwa Deborah
Dobbe, Roel
Computers and Society
Artificial Intelligence
As AI systems proliferate in society, the AI community is increasingly preoccupied with the concept of AI Safety, namely the prevention of failures due to accidents that arise from an unanticipated departure of a system's behavior from designer intent in AI deployment. We demonstrate through an analysis of real world cases of such incidents that although current vocabulary captures a range of the encountered issues of AI deployment, an expanded socio-technical framing will be required for a more complete understanding of how AI systems and implemented safety mechanisms fail and succeed in real life.
title Concrete Problems in AI Safety, Revisited
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2401.10899