x

LESSWRONG

LW

Matthew Barnett's Shortform — LessWrong

Matthew Barnett's Shortform

by Matthew Barnett

9th Aug 2019

AI Alignment Forum

1 min read

7

Ω 2

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

Rendering 0/392 comments, sorted by

(show all) Click to highlight new comments since: Today at 4:33 PM

More from Matthew Barnett

Curated and popular this week

392

Comment Permalink

Similar to how rewarding a student for their actual grades on a final exam will be more effective in getting them to learn the material than rewarding them merely for how hard they tried

Evidence for this?

Mentioned in

146My thoughts on the social response to AI risk

59Testing for Scheming with Model Deletion

29The jailbreak argument against LLM values

17Will AI and Humanity Go to War?

5(Non-deceptive) Suboptimality Alignment