Jesse Clifton

Nov 5, 2024 | lesswrong.com | Anthony DiGiovanni |Jesse Clifton

In our jobs as AI safety researchers, we think a lot about what it means to have reasonable beliefs and to make good decisions. This matters because we want to understand how powerful AI systems might behave. It also matters because we ourselves need to know how to make good decisions in light of tremendous uncertainty about how to shape the long-term future.

Jul 17, 2024 | lesswrong.com | Nicolas Macé |Anthony DiGiovanni |Jesse Clifton

Agents might fail to peacefully trade in high-stakes negotiations. Such bargaining failures can have catastrophic consequences, including great power conflicts, and AI flash wars. This post is a distillation of DiGiovanni et al. (2024) (DCM), whose central result is that agents that are sufficiently transparent to each other have individual incentives to avoid catastrophic bargaining failures.

Jul 10, 2023 | lesswrong.com | Nicolas Macé |Jesse Clifton |Daniel Kokotajlo |Sylvester Kollin

Thanks Dagon:Any mechanism to revoke or change a commitment is directly giving up value IN THE COMMON FORMULATION of the problemCan you say more about what you mean by “giving up value”? Our contention is that the ex-ante open-minded agent is not giving up (expected) value, in the relevant sense, when they "revoke their commitment" upon becoming aware of certain possible counterpart types.