Charlie Steiner

Karma: 7,879

If you want to chat, message me!

LW1.0 username Manfred. PhD in condensed matter physics. I am independently thinking and writing about value learning.

Take 4: One problem with natural abstractions is there’s too many of them.

Charlie SteinerDec 5, 2022, 10:39 AM

37 points

4 comments1 min readLW link

Take 3: No indescribable heavenworlds.

Charlie SteinerDec 4, 2022, 2:48 AM

23 points

12 comments2 min readLW link

Take 2: Building tools to help build FAI is a legitimate strategy, but it’s dual-use.

Charlie SteinerDec 3, 2022, 12:54 AM

17 points

1 comment2 min readLW link

Take 1: We’re not going to reverse-engineer the AI.

Charlie SteinerDec 1, 2022, 10:41 PM

38 points

4 comments4 min readLW link

Some ideas for epistles to the AI ethicists

Charlie SteinerSep 14, 2022, 9:07 AM

19 points

0 comments4 min readLW link

The Solomonoff prior is malign. It’s not a big deal.

Charlie SteinerAug 25, 2022, 8:25 AM

43 points

9 comments7 min readLW link

Reducing Goodhart: Announcement, Executive Summary

Charlie SteinerAug 20, 2022, 9:49 AM

16 points

0 comments1 min readLW link

Reading the ethicists 2: Hunting for AI alignment papers

Charlie SteinerJun 6, 2022, 3:49 PM

24 points

2 comments7 min readLW link

Reading the ethicists: A review of articles on AI in the journal Science and Engineering Ethics

Charlie SteinerMay 18, 2022, 8:52 PM

50 points

8 comments14 min readLW link

Thoughts on AI Safety Camp

Charlie SteinerMay 13, 2022, 7:16 AM

33 points

8 comments7 min readLW link

New year, new research agenda post

Charlie SteinerJan 12, 2022, 5:58 PM

29 points

4 comments16 min readLW link

Supervised learning and self-modeling: What’s “superhuman?”

Charlie SteinerDec 9, 2021, 12:44 PM

13 points

1 comment8 min readLW link

Goodhart: Endgame

Charlie SteinerNov 19, 2021, 1:26 AM

25 points

3 comments8 min readLW link

Models Modeling Models

Charlie SteinerNov 2, 2021, 7:08 AM

23 points

5 comments10 min readLW link

Goodhart Ethology

Charlie SteinerSep 17, 2021, 5:31 PM

20 points

4 comments14 min readLW link

Competent Preferences

Charlie SteinerSep 2, 2021, 2:26 PM

30 points

2 comments6 min readLW link

Introduction to Reducing Goodhart

Charlie SteinerAug 26, 2021, 6:38 PM

48 points

10 comments4 min readLW link

How to turn money into AI safety?

Charlie SteinerAug 25, 2021, 10:49 AM

66 points

26 comments8 min readLW link

HCH Speculation Post #2A

Charlie SteinerMar 17, 2021, 1:26 PM

43 points

7 comments9 min readLW link

Hierarchical planning: context agents

Charlie SteinerDec 19, 2020, 11:24 AM

22 points

6 comments9 min readLW link