flâneur — a map of the web's best reading

Competing with sampling — Alignment Research Center

alignment.org · 10,060 words · saved by 3 readers

In 2025, ARC has been making conceptual and theoretical progress at the fastest pace that I've seen since I first interned in 2022. Most of this progress has come about because of a re-orientation around a more specific goal: outperforming random sampling when it comes to understanding neural

In 2025, ARC has been making conceptual and theoretical progress at the fastest pace that I've seen since I first interned in 2022. Most of this progress has come about because of a re-orientation around a more specific goal: outperforming random sampling when it comes to understanding neural network outputs. Compared to our previous goals, this goal has the advantage of being more concrete and more directly tied to useful applications. The purpose of this post is to: Explain and motivate our "outperforming sampling" agenda from the standpoint of preventing catastrophic AI misalignment. Introd

Explore this link on the map →

saved by

related reading