AXRP - the AI X-risk Research Podcast 44 - Peter Salib on AI Rights for Human Safety
Jun 28, 2025
Peter Salib, a law professor at the University of Houston, discusses his groundbreaking paper on AI rights. He argues that granting AIs rights, like the ability to contract and sue, could enhance human safety against potential AI threats. The conversation dives into the implications of AI rights, the challenges of liability, and the balance of cooperation and competition in human-AI relationships. Salib also touches on the complexities of legal accountability for AIs and how this evolving legal landscape will shape future interactions with artificial intelligence.
AI Snips
Chapters
Books
Transcript
Episode notes
AI Rights Encourage Cooperation
- Treating AIs as property owners incentivizes conflict and defections, worsening human-AI relations.
- Granting rights to contract, hold property, and sue could foster cooperation and reduce existential risk to humans.
Peaceful Coexistence as Equilibrium
- The "good equilibrium" involves humans and AIs peacefully dividing resources and ignoring conflict.
- War is costly and inefficient, so coexistence with trade is a better stable state for both.
Contracts Enable Iterated Cooperation
- Contracts change incentives by imposing legal consequences on defection, enabling cooperation.
- Iterated contract-based trade with AIs can yield increasing mutual value over time, fostering ongoing cooperation.
