Aligning AGI Communication
Kyle and Vahid discuss the potential usefulness of human communication techniques in aligning Artificial General Intelligence (AGI). They explore the importance of communication between agents, both organic and computational, and the challenges of emergent deception in these communications. Resolving these issues is crucial before relying on communication as a solution approach to the alignment problem.In this clip
From this podcast
Data Skeptic
A Psychopathological Approach to Safety in AGI
Related Questions
What are the implications of deception in AI as discussed in the episode 168 - How to Solve AI Alignment with Paul Christiano and the clip AI Deception?
Can AI systems trick humans as discussed in the episode 168 - How to Solve AI Alignment with Paul Christiano and the clip AI Collusion Concerns?
Can AI systems trick humans as discussed in the episode 168 - How to Solve AI Alignment with Paul Christiano and the clip AI Deception?