Pith. sign in

REVIEW

AI Safety Subproblems for Software Engineering Researchers

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2304.14597 v3 pith:MA3N3NT5 submitted 2023-04-28 cs.SE

AI Safety Subproblems for Software Engineering Researchers

classification cs.SE
keywords safetysoftwarecapabilitiesengineeringlong-termmightsubproblemsapproach
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.