Abstract
Suppose an artificial agent
a
adj
{a}_{\text{adj}}
, as time unfolds, (i) receives from multiple artificial agents (which may, in turn, themselves have received from yet other such agents…) propositional content, and (ii) must solve an ethical problem on the basis of what it has received. How should
a
adj
{a}_{\text{adj}}
adjudicate what it has received in order to produce such a solution? We consider an environment infused with logicist artificial agents
a
1
,
a
2
,
…
,
a
n
{a}_{1},{a}_{2},\ldots ,{a}_{n}
that sense and report their findings to “adjudicator” agents who must solve ethical problems. (Many if not most of these agents may be robots.) In such an environment, inconsistency is a virtual guarantee:
a
adj
{a}_{\text{adj}}
may, for instance, receive a report from
a
1
{a}_{1}
that proposition
ϕ
\phi
holds, then from
a
2
{a}_{2}
that
¬
ϕ
\neg \phi
holds, and then from
a
3
{a}_{3}
that neither
ϕ
\phi
nor
¬
ϕ
\neg \phi
should be believed, but rather
ψ
\psi
instead, at some level of likelihood. We further assume that agents receiving such incompatible reports will nonetheless sometimes simply need, before long, to make decisions on the basis of these reports, in order to try to solve ethical problems. We provide a solution to such a quandary: AI capable of adjudicating competing reports from subsidiary agents through time, and delivering to humans a rational, ethically correct (relative to underlying ethical principles) recommendation based upon such adjudication. To illuminate our solution, we anchor it to a particular scenario.
Can a Robot Lie? Exploring the Folk Concept of Lying as Applied to Artificial Agents
