Dissent Collusion

Screwtape10 Aug 2022 2:43 UTC

7 points

0 comments3 min readLW link

Proposal: Consider not using distance-direction-dimension words in abstract discussions

moridinamael9 Aug 2022 20:44 UTC

42 points

7 comments5 min readLW link

[Question] How would two superintelligent AIs interact, if they are unaligned with each other?

Nathan11239 Aug 2022 18:58 UTC

4 points

6 comments1 min readLW link

Disagreements about Alignment: Why, and how, we should try to solve them

ojorgensen9 Aug 2022 18:49 UTC

7 points

0 comments16 min readLW link

Progress links and tweets, 2022-08-09

jasoncrawford9 Aug 2022 17:35 UTC

7 points

2 comments1 min readLW link

(rootsofprogress.org)

Content generation. Where do we draw the line?

Q Home9 Aug 2022 10:51 UTC

6 points

4 comments2 min readLW link

Introduction to Constructor Theory

AlfredHarwood9 Aug 2022 10:28 UTC

1 point

0 comments9 min readLW link

[Question] What are some alternatives to Shapley values which drop additivity?

eapi9 Aug 2022 9:16 UTC

6 points

0 comments1 min readLW link

(math.stackexchange.com)

Team Shard Status Report

David Udell9 Aug 2022 5:33 UTC

35 points

2 comments3 min readLW link

Announcing: Mechanism Design for AI Safety—Reading Group

Rubi9 Aug 2022 4:21 UTC

13 points

0 comments4 min readLW link

[Question] What are some Works that might be useful but are difficult, so forgotten?

TekhneMakre9 Aug 2022 2:22 UTC

8 points

2 comments1 min readLW link

Project proposal: Testing the IBP definition of agent

Jeremy Gillen, Thomas Larsen and AtlasOfCharts

9 Aug 2022 1:09 UTC

9 points

3 comments2 min readLW link

How (not) to choose a research project

Garrett Baker, CatGoddess and Johannes C. Mayer

9 Aug 2022 0:26 UTC

67 points

11 comments7 min readLW link

[Question] Are ya winning, son?

Nathan11239 Aug 2022 0:06 UTC

13 points

13 comments2 min readLW link

General alignment properties

TurnTrout8 Aug 2022 23:40 UTC

35 points

1 comment1 min readLW link

Encultured AI, Part 1 Appendix: Relevant Research Examples

Andrew_Critch and Nick Hay

8 Aug 2022 22:44 UTC

9 points

1 comment7 min readLW link

Encultured AI, Part 1: Enabling New Benchmarks

Andrew_Critch and Nick Hay

8 Aug 2022 22:44 UTC

56 points

2 comments6 min readLW link

Broad Basins and Data Compression

Jeremy Gillen, Stephen Fowler and Thomas Larsen

8 Aug 2022 20:33 UTC

17 points

5 comments7 min readLW link

Interpretability/Tool-ness/Alignment/Corrigibility are not Composable

johnswentworth8 Aug 2022 18:05 UTC

86 points

6 comments3 min readLW link

A sufficiently paranoid paperclip maximizer

RomanS8 Aug 2022 11:17 UTC

15 points

10 comments2 min readLW link