Benja Fallenstein

TL;DR: This work considers the one-shot Prisoner's Dilemma between algorithms with read-access to one anothers' source codes, and uses the modal logic of provability to build agents that can achieve mutual cooperation in a manner that is robust, in that cooperation does not require exact equality of the agents' source code.

TL;DR: It is shown that in one particular model based on formal logic, naive approaches either lead to incorrect reasoning that allows an agent to put off an important task forever (the procrastination paradox), or fail to allow the agent to justify even obviously safe rewrites (the Lobian obstacle).

TL;DR: This paper proposes a framework in which agents and their environments are both modelled as probablistic oracle machines with access to a “reflective” oracle, which is able to answer questions about the outputs of other machines with Access to the same oracle.

TL;DR: In this article, the authors present a reflection principle of the form "If the cardinality of a cardinal is provable, then the cardinal has the same meaning both inside and outside of the HOL4 theorem prover".