Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.

tl;dr: There's two diametrically opposed failure modes an alignment researcher can fall into: engaging in excessively concrete research whose findings won't timely generalize to AGI, and engaging in excessively abstract research whose findings won't timely connect to the practical reality.

Different people's assessments of what research is too abstract/concrete differ significantly based on their personal AI-Risk models. One person's too-abstract can be another's too-concrete.

The meta-level problem of alignment research is to pick a research direction that, on your subjective model of AI Risk, strikes a good balance between the two – and thereby arrives at the solution to alignment in as few steps as possible.

Introduction.

Suppose that you're interested in solving AGI Alignment. There's a dizzying plethora of approaches to choose from:

What behavioral properties do the current-best AIs exhibit?
Can we already [...]

---

Outline:

(03:53) The Scylla: Atheoretic Empiricism

(06:01) The Charybdis: Out-of-Touch Theorizing

(08:13) The Shortest Path

---

First published:
December 18th, 2023

Source:
https://www.lesswrong.com/posts/Zn3iF8qfFFWRrrZNR/the-shortest-path-between-scylla-and-charybdis

---

Narrated by TYPE III AUDIO.

“The Shortest Path Between Scylla and Charybdis” by Thane Ruthenis

LessWrong (30+ Karma)