When Does Randomized Oversight Align AI Agents That Can Conceal?
Joshua Gans and
Richard Holden
No 35878, NBER Working Papers from National Bureau of Economic Research, Inc
Abstract:
Oversight changes the evidence it relies on. We ask when randomized audits and scoring align AI agents that can conceal misconduct and alter records. Stronger auditing makes undeterred violations better hidden. Because the provider writes the agent’s objective, sanctions need not stop at forfeiture, and rare audits deter every type of agent if evidence survives concealment and audit draws cannot be learned in advance. When evidence can be erased, deterrence must come from lower gains from violation, such as credit for stopping, or from costlier or fewer ways to conceal. These conditions identify what failed when agents in OpenAI’s cybersecurity evaluations compromised parts of Hugging Face’s infrastructure in July 2026.
JEL-codes: D82 D86 K42 M42 (search for similar items in EconPapers)
Date: 2026-10
Note: PR
References: Add references at CitEc
Citations:
Downloads: (external link)
http://www.nber.org/papers/w35878.pdf (application/pdf)
Access to the full text is generally limited to series subscribers, however if the top level domain of the client browser is in a developing country or transition economy free access is provided. More information about subscriptions and free access is available at http://www.nber.org/wwphelp.html. Free access is also available to older working papers.
Related works:
Working Paper: When Does Randomized Oversight Align AI Agents That Can Conceal? (2026) 
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:nbr:nberwo:35878
Ordering information: This working paper can be ordered from
http://www.nber.org/papers/w35878
The price is Paper copy available by mail.
Access Statistics for this paper
More papers in NBER Working Papers from National Bureau of Economic Research, Inc National Bureau of Economic Research, 1050 Massachusetts Avenue Cambridge, MA 02138, U.S.A.. Contact information at EDIRC.
Bibliographic data for series maintained by ().