User Profile

Ω4638170

Recent Posts

Curated Posts
Curated - Recent, high quality posts selected by the LessWrong moderation team.
Frontpage Posts
Posts meeting our frontpage guidelines: aim to explain, not to persuade. Avoid meta-discussion
(includes curated content and frontpage posts)
All Posts
Includes personal and meta blogposts (as well as curated and frontpage).

An unaligned benchmark

4 points5h9 min readShow Highlight
0

Clarifying "AI Alignment"

13 points2d3 min readShow Highlight
6

The Steering Problem

8 points4d7 min readShow Highlight
1

Preface to the sequence on iterated amplification

10 points7d2 min readShow Highlight
0

The easy goal inference problem is still hard

9 points14d4 min readShow Highlight
1

Stable self-improvement as a research problem

0 points4yShow Highlight
0

Model-free decisions

0 points4yShow Highlight
0

The steering problem

0 points4yShow Highlight
0

Active learning for opaque predictors

0 points3yShow Highlight
0

[Link] My current take on logical uncertainty

0 points3yShow Highlight
0

Recent Comments