So once we’ve eliminated or reduced deceptive alignment and outer alignment issues, there’s not much else to do but turn on the AGI.
This is an argument for feasibility of making the first AGIs aligned. Which doesn’t make them safer than humans, able to avoid/prevent building of the actually dangerous AGIs with different designs shortly thereafter.
This is an argument for feasibility of making the first AGIs aligned. Which doesn’t make them safer than humans, able to avoid/prevent building of the actually dangerous AGIs with different designs shortly thereafter.