Unpredictability of AI

Roman V. Yampolskiy

Unpredictability of AI

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1905.13053 v1 pith:FVU7XA4Q submitted 2019-05-29 cs.AI cs.SYeess.SY

Unpredictability of AI

Roman V. Yampolskiy This is my paper

classification cs.AI cs.SYeess.SY

keywords unpredictabilitysafetysystemachieveactionschallengesconclusionconsistently

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

The young field of AI Safety is still in the process of identifying its challenges and limitations. In this paper, we formally describe one such impossibility result, namely Unpredictability of AI. We prove that it is impossible to precisely and consistently predict what specific actions a smarter-than-human intelligent system will take to achieve its objectives, even if we know terminal goals of the system. In conclusion, impact of Unpredictability on AI Safety is discussed.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

Unexplainability and Incomprehensibility of Artificial Intelligence
cs.CY 2019-06 unverdicted novelty 3.0

Advanced AI systems are unexplainable in full and produce explanations that humans cannot comprehend.