Journal article icon

Journal article

Will AI avoid exploitation? Artificial general intelligence and expected utility theory

Abstract:
A simple argument suggests that we can fruitfully model advanced AI systems using expected utility theory. According to this argument, an agent will need to act as if maximising expected utility if they’re to avoid exploitation. Insofar as we should expect advanced AI to avoid exploitation, it follows that we should expected advanced AI to act as if maximising expected utility. I spell out this argument more carefully and demonstrate that it fails, but show that the manner of its failure is instructive: in exploring the argument, we gain insight into how to model advanced AI systems.
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1007/s11098-023-02023-4

Authors


More by this author
Institution:
University of Oxford
Division:
HUMS
Department:
Philosophy Faculty
Role:
Author


Publisher:
Springer
Journal:
Philosophical Studies More from this journal
Volume:
182
Issue:
7
Pages:
1519-1538
Publication date:
2023-08-05
Acceptance date:
2023-07-16
DOI:
EISSN:
1573-0883
ISSN:
0031-8116


Language:
English
Keywords:
Pubs id:
1493167
Local pid:
pubs:1493167
Deposit date:
2023-07-18

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP