Episode Details
Back to Episodes“9 kinds of hard-to-verify tasks” by Cleo Nardo
Published 1 day, 7 hours ago
Description
Introduction
Some people talk about "hard-to-verify tasks" and "easy-to-verify tasks" like these are both natural kinds. But I think splitting tasks into "easy-to-verify" and "hard-to-verify" is like splitting birds into ravens and non-ravens.
- Easy-to-verify tasks are easy for the same reason — there's a known short program that takes a task specification and a candidate solution, and outputs a score, without using substantial resources or causing undesirable side effects.
- By contrast, "hard-to-verify tasks" is a negative category — it just means no such program exists. But there are many kinds, corresponding to different reasons no such program exists.
Listing kinds of hard-to-verify tasks
I might update the list if I think of more, or if I see additional suggestions in the comments.
- Verification requires expensive AI inference. A verifier exists and works fine, but each run costs enough compute that you can't afford the number of labels you'd want.
- Given two proposed SAE experiments, say which will be more informative. Running both to find out costs $100–$1000 per comparison.
- Given two research agendas (e.g. pragmatic vs ambitious mech interp), say which produces more alignment progress. Same structure, but each comparison costs millions.
- Verification requires expensive human time. The verifier [...]
---
Outline:
(00:10) Introduction
(00:55) Listing kinds of hard-to-verify tasks
(04:38) Implications
---
First published:
April 20th, 2026
Source:
https://www.lesswrong.com/posts/NEscrkxr9SxHpGayB/9-kinds-of-hard-to-verify-tasks
---
Narrated by TYPE III AUDIO.