AI ALIGNMENT FORUMScott Garrabrant
AF

User Profile

Ω1177147

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

Topological Fixed Point Exercises

Scott Garrabrant, Sam Eisenstat
8 points21h3 min readShow Highlight
0

Fixed Point Exercises

Scott Garrabrant
7 points21h1 min readShow Highlight
0

Embedded Agency (full-text version)

Scott Garrabrant, Abram Demski
9 points2d42 min readShow Highlight
1

Embedded Curiosities

Scott Garrabrant
15 points9d2 min readShow Highlight
0

History of the Development of Logical Induction

Scott Garrabrant
4 points3mo4 min readShow Highlight
2

Prisoners' Dilemma with Costs to Modeling

Scott Garrabrant
1 point5mo7 min readShow Highlight
1

(A -> B) -> A

Scott Garrabrant
7 points2mo4 min readShow Highlight
1

Optimization Amplifies

Scott Garrabrant
1 point5mo3 min readShow Highlight
0

Bayesian Probability is for things that are Space-like Separated from You

Scott Garrabrant
12 points4mo1 min readShow Highlight
1

Robustness to Scale

Scott Garrabrant
3 points9mo1 min readShow Highlight
0
Load More...  

Recent Comments