•

Applied to Leaving MIRI, Seeking Funding by MondSemmel ago

In a deterministic logical system, assuming that all agents will share the same axioms, "trust" arises from being able to formally prove that the conclusions reached by any subsequently generated agents will be true. The possibility to be able to have this form of trust is influenced by Lö~~bs~~b's theorem. The inability to form this trust is called the Löbian obstacle.

This leads to the question: How can the original agent trust that these recursively generated agents maintain goals that are similar to the original's ~~objective ?~~objective?

This leads to the ~~question :~~question: How can the original agent trust that these recursively generated agents maintain goals that are similar to the original's objective ?

In a deterministic logical system, assuming that all agents will share the same ~~axioms ,~~axioms, "trust" arises from being able to formally prove that the conclusions reached by any subsequently generated agents will be true. The possibility to be able to have this form of trust is influenced by Löbs theorem. The inability to form this trust is called the Löbian obstacle.

An agent might have the ability to create similar or slightly better versions of ~~itself , these~~itself. These new agents can in turn create similar / better versions of themselves, and so on in a repeating pattern. This is referred to as an agent **tiling** itself.

•

Applied to The Löbian Obstacle, And Why You Should Care by lukemarks ago

**See Also :Also:** Löbian

In a deterministic logical ~~system ,~~system, assuming that all agents will share the same axioms , "trust" arises from being able to formally prove that the conclusions reached by any subsequently generated agents will be true. The possibility to be able to have this form of trust is influenced by Löbs theorem. The inability to form this trust is called the Löbian obstacle.

•

Applied to Higher Dimension Cartesian Objects and Aligning ‘Tiling Simulators’ by lukemarks ago

•

Applied to The alignment stability problem by Noosphere89 ago

•

Applied to "Corrigibility at some small length" by dath ilan by Christopher King ago

In a deterministic logical system , assuming that all agents will share the same axioms , "trust" arises from being able to formally prove that the ~~conculsions~~conclusions reached by any subsequently generated agents will be true. The possibility to be able to have this form of trust is influenced by Löbs theorem. The inability to form this trust is called the Löbian obstacle.

•

Applied to Vingean Reflection: Open Problems by Linda Linsefors ago

•

•

Applied to Paraconsistent Tiling Agents (Very Early Draft) by Linda Linsefors ago

•

Applied to Tiling agents with transfinite parametric polymorphism by Linda Linsefors ago

•

Applied to Walkthrough of the Tiling Agents for Self-Modifying AI paper by Linda Linsefors ago

•

Applied to Making Vaccine by Linda Linsefors ago

This leads to the question: How can the original agent trust that these recursively generated agents maintain goals that are similar to the

~~original'~~original agent's objective?