x

LESSWRONG

LW

Michael Thiessen's Shortform — LessWrong

Michael Thiessen's Shortform

by Michael Thiessen

1st Apr 2024

1 min read

2

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

Rendering 0/7 comments, sorted by

(show all) Click to highlight new comments since: Today at 7:52 PM

More from Michael Thiessen

Curated and popular this week

7

Comment Permalink

Jeff Schecter1mo11

Better sandboxing has a very practical and straightforward effect on prosaic alignment!

Leaky sandboxes cause more rewards for cheating during RLHF.

Rewards for egregious behavior during training cause egregious behavior in deployment.