AI ALIGNMENT FORUMpaulfchristiano
AF

User Profile

Ω4638170

Sequences

Iterated Amplification

Recent Posts

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

An unaligned benchmark

Paul Christiano
4 points5h9 min readShow Highlight
0

Clarifying "AI Alignment"

Paul Christiano
13 points2d3 min readShow Highlight
6

The Steering Problem

Paul Christiano
8 points4d7 min readShow Highlight
1

Preface to the sequence on iterated amplification

Paul Christiano
10 points7d2 min readShow Highlight
0

The easy goal inference problem is still hard

Paul Christiano
9 points14d4 min readShow Highlight
1

Stable self-improvement as a research problem

Paul Christiano
0 points4yShow Highlight
0

Model-free decisions

Paul Christiano
0 points4yShow Highlight
0

The steering problem

Paul Christiano
0 points4yShow Highlight
0

Active learning for opaque predictors

Paul Christiano
0 points3yShow Highlight
0

[Link] My current take on logical uncertainty

Paul Christiano
0 points3yShow Highlight
0
Load More...  

Recent Comments