Top postsTop post
Samuel Dylan Martin
2297
Ω
390
14
281
We analyze three prominent strategies for governing transformative AI (TAI) development: Cooperative Development, Strategic Advantage, and Global Moratorium. We evaluate these strategies across varying levels of alignment difficulty and development timelines, examining their effectiveness in preventing catastrophic risks while preserving beneficial AI development. Our analysis reveals that strategy preferences shift...
This article revisits and expands upon the AI alignment difficulty scale, a framework for understanding the increasing challenges of aligning artificial intelligence systems with human values. We explore how alignment difficulties evolve from simple goal misalignment to complex scenarios involving deceptive alignment and gradient hacking as we progress up the...
This work was funded by Polaris Ventures As AI systems become more integrated into society, we face potential societal-scale risks that current regulations fail to address. These risks include cooperation failures, structural failures from opaque decision-making, and AI-enabled totalitarian control. We propose enhancing LLM-based AI Constitutions and Model Specifications to...
Introduction Polarisation hampers cooperation and progress towards understanding whether future AI poses an existential risk to humanity and how to reduce the risks of catastrophic outcomes. It is exceptionally challenging to pin down what these risks are and what decisions are best. We believe that a model-based approach offers many...
Image from https://threadreaderapp.com/thread/1666482929772666880.html Chris Olah recently released a tweet thread describing how the Anthropic team thinks about AI alignment difficulty. On this view, there is a spectrum of possible scenarios ranging from ‘alignment is very easy’ to ‘alignment is impossible’, and we can frame AI alignment research as a process...
In this post, we look at conditions under which Intent Alignment isn't Sufficient or Intent Alignment isn't Necessary for interventions on AGI systems to reduce the risks of (unendorsed) conflict to be effective. We then conclude this sequence by listing what we currently think are relatively promising directions for technical...
Here we will look at two of the claims introduced in the previous post: AGIs might not avoid conflict that is costly by their lights (Capabilities aren’t Sufficient) and conflict that is costly by our lights might not be costly by the AGIs’ (Conflict isn’t Costly). Explaining costly conflict First...