evhub's Shortform

evhub

LESSWRONG

LW

LESSWRONG

LW

evhub's Shortform

by evhub

11th Jun 2022

AI Alignment Forum

1 min read

301

13 Ω 10

This is a special post for quick takes by evhub. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.

Rendering 0/301 comments, sorted by

top scoring

(show all) Click to highlight new comments since: Today at 11:18 AM

Moderation Log

evhub's Shortform

by evhub

11th Jun 2022

AI Alignment Forum

1 min read

301

13 Ω 10

This is a special post for quick takes by evhub. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.

Mentioned in

242Labs’ current alignment plans seem terrible

155Current alignment techniques might be ineffective (and actively bad) in the age of RL

99How to pace the US frontier

93SOTA alignment assessments don’t strongly update us against misalignment

62Towards embedded evaluations for scheming propensities

Load More (5/16)

Rendering 0/301 comments, sorted by

top scoring

(show all) Click to highlight new comments since: Today at 11:18 AM

Moderation Log