Top 10 alignmentforum.org Competitors

lesswrong.com

A community blog devoted to refining the art of rationality

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.

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.

matsprogram.org

Meet MATS mentors advancing AI alignment, transparency, and security. Leading researchers from Anthropic, DeepMind, Redwood Research, and more.

ai-2027.com

A research-backed AI scenario forecast.

anthropic.com

Hybrid reasoning model with fast, capable intelligence for real-time agents and high-volume work, featuring a 1M context window

openreview.net

Promoting openness in scientific communication and the peer-review process

80000hours.org

Your career is not only a major driver of your happiness — it’s probably also your biggest opportunity to have a positive impact on the world.

lilianweng.github.io

Document my learning notes.