arXiv Open Access 2023

AI Safety Subproblems for Software Engineering Researchers

David Gros Prem Devanbu Zhou Yu

Lihat Sumber

Abstrak

In this 4-page manuscript we discuss the problem of long-term AI Safety from a Software Engineering (SE) research viewpoint. We briefly summarize long-term AI Safety, and the challenge of avoiding harms from AI as systems meet or exceed human capabilities, including software engineering capabilities (and approach AGI / "HLMI"). We perform a quantified literature review suggesting that AI Safety discussions are not common at SE venues. We make conjectures about how software might change with rising capabilities, and categorize "subproblems" which fit into traditional SE areas, proposing how work on similar problems might improve the future of AI and SE.

Topik & Kata Kunci

cs.SE

Penulis (3)

David Gros

Prem Devanbu

Zhou Yu

Format Sitasi

APA MLA BibTeX

Gros, D., Devanbu, P., Yu, Z. (2023). AI Safety Subproblems for Software Engineering Researchers. https://arxiv.org/abs/2304.14597

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2023
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓