Trust and Its Betrayal under Three Representational Strategies
arXiv cs.AIen
arXiv:2608.00321v1 Announce Type: new Abstract: Trust is a propositional attitude of a distinctive kind: to trust is to rely on another under conditions where reliance could be disappointed, and the disappointment of trust---betrayal---differs qualitatively from the disappointment of a prediction. We treat trust as a \emph{subjunctive} epistemic state: $A$ trusts $B$'s competence when $A$ believes that \emph{were $P$ true, $B$ would know it}, and $B$'s integrity when $A$ believes that \emph{were $B$ to know $P$, he would disclose it to $A$}. We develop three representations of this state---as lexicographic \emph{assumption} as \emph{ordinal closeness} in a Lewis--Stalnaker sphere system , an
This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.
Read the full story at arXiv cs.AI- Verktyg
- Forskning
Related AI news
- Högre chefer missbrukar skugg-AI dubbelt så ofta som vanliga anställdaComputer Sweden · August 4, 2026
- Avec l’introduction des « aperçus IA », « le Web et les applications mobiles pourraient n’avoir été qu’une étape intermédiaire dans la transformation numérique »Le Monde Pixels · August 4, 2026
- Enhancing LLMs with Context-Specific Knowledge for Mitigating Misinformation in SMEs: A RAG-based Modeling and AnalysisarXiv cs.AI · August 4, 2026
- Can LLM Agents Price Competitively? A Dynamic Multi-Attribute Auction Benchmark for Agentic CommercearXiv cs.AI · August 4, 2026
- Memory Reward Inflation in Self-Improving LLM AgentsarXiv cs.AI · August 4, 2026
- AutoFOAM: The Self-Refining Autonomous OpenFOAM AgentarXiv cs.AI · August 4, 2026