As an employee of the European AI Office, it's important for me to emphasize this point: The views and opinions of the author expressed herein are personal and do not necessarily reflect those of the European Commission or other EU institutions.

Also, to stave off a common confusion: I worked at ARC Theory, which is now simply called ARC, on Paul Christiano's theoretical alignment agenda. The more famous ARC Evals was a different group working on evaluations, their work was completely separate from ARC Theory, and they were only housed under the same organization out of convenience, until ARC Evals spun off under the name METR. Nothing I write here has any implication about the work of ARC Evals/METR in any way.

Personal introduction

From October 2023 to January 2025, I worked as a theoretical researcher at Alignment Research Center.

While working at ARC, I noticed that many [...]

---

Outline:

(00:56) Personal introduction

(05:30) The birds eye view

(07:33) Explaining everything

(10:14) Empirical regularities

(12:43) Capacity allocation in explanation-finding

(17:38) Assuming a catastrophe detector

(20:20) Explaining behavior dependent on outside factors

(22:17) Teleological explanations

(24:06) When and what do we explain?

(26:06) Explaining algorithmic tasks

The original text contained 18 footnotes which were omitted from this narration.

---

First published:
April 30th, 2025

Source:
https://www.lesswrong.com/posts/xtcpEceyEjGqBCHyK/obstacles-in-arc-s-agenda-finding-explanations

---

Narrated by TYPE III AUDIO.

“Obstacles in ARC’s agenda: Finding explanations” by David Matolcsi

LessWrong (30+ Karma)