neelnanda.ioの競合サイトトップ10

alignmentforum.org

A community blog devoted to technical AI alignment research

lesswrong.com

A community blog devoted to refining the art of rationality

matsprogram.org

Winter 2024

transformer-circuits.pub

We investigate the internal mechanisms used by Claude 3.5 Haiku — Anthropic's lightweight production model — in a variety of contexts, using our circuit tracing methodology.

arxiv.org

A system of non-tradable credits that flow between individuals like karma, hence proposed under that name, is a mechanism for repeated resource allocation that comes with attractive efficiency and fairness properties, in theory. In this study, we test karma in an online experiment in which human subjects repeatedly compete for a resource with time-varying and stochastic individual preferences or urgency to acquire the resource. We confirm that karma has significant and sustained welfare benefits even in a population with no prior training. We identify mechanism usage in contexts with sporadic high urgency, more so than with frequent moderate urgency, and implemented as a simple (binary) karma bidding scheme as particularly effective for welfare improvements: relatively larger aggregate efficiency gains are realized that are (almost) Pareto superior. These findings provide guidance for further testing and for future implementation plans of such mechanisms in the real world.

github.com

Join the world's most widely adopted, AI-powered developer platform where millions of developers, businesses, and the largest open source community build software that advances humanity.

medium.com

Read stories about Support on Medium. Discover smart, unique perspectives on Support and the topics that matter most to you like Mental Health, Love, Community, Relationships, Friendship, Life, Tech, Writing, Family, and more.

linkedin.com

1 billion members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.