The Fusion Power Generator Scenario

8 Aug 2020 18:31 UTC

42 points

9 comments3 min readLW link

Analyzing the Problem GPT-3 is Trying to Solve

6 Aug 2020 21:58 UTC

15 points

2 comments4 min readLW link

Measuring hardware overhang

5 Aug 2020 19:59 UTC

32 points

4 comments4 min readLW link

[AN #111]: The Circuits hypotheses for deep learning

5 Aug 2020 17:40 UTC

23 points

0 comments9 min readLW link

(mailchi.mp)

Infinite Data/Compute Arguments in Alignment

4 Aug 2020 20:21 UTC

41 points

6 comments2 min readLW link

Interpretability in ML: A Broad Overview

lifelonglearner

4 Aug 2020 19:03 UTC

29 points

0 comments15 min readLW link

Three mental images from thinking about AGI debate & corrigibility

3 Aug 2020 14:29 UTC

41 points

35 comments4 min readLW link

[Question] What are the most important papers/post/resources to read to understand more of GPT-3?

2 Aug 2020 20:53 UTC

25 points

3 comments1 min readLW link

Inner Alignment: Explain like I’m 12 Edition

1 Aug 2020 15:24 UTC

98 points

8 comments12 min readLW link

Power as Easily Exploitable Opportunities

1 Aug 2020 2:14 UTC

26 points

5 comments6 min readLW link

“Go west, young man!”—Preferences in (imperfect) maps

Stuart_Armstrong

31 Jul 2020 7:50 UTC

19 points

10 comments3 min readLW link

[Question] What if memes are common in highly capable minds?

Daniel Kokotajlo

30 Jul 2020 20:45 UTC

24 points

5 comments2 min readLW link

Learning the prior and generalization

29 Jul 2020 22:49 UTC

32 points

10 comments4 min readLW link

What Failure Looks Like: Distilling the Discussion

29 Jul 2020 21:49 UTC

53 points

10 comments7 min readLW link

[AN #110]: Learning features from human feedback to enable reward learning

29 Jul 2020 17:20 UTC

13 points

2 comments10 min readLW link

(mailchi.mp)

The “best predictor is malicious optimiser” problem

29 Jul 2020 11:49 UTC

14 points

10 comments2 min readLW link

[Question] What happens to variance as neural network training is scaled? What does it imply about “lottery tickets”?

28 Jul 2020 20:22 UTC

23 points

2 comments1 min readLW link

[Question] To what extent are the scaling properties of Transformer networks exceptional?

28 Jul 2020 20:06 UTC

25 points

1 comment1 min readLW link

[Question] Does the lottery ticket hypothesis suggest the scaling hypothesis?

Daniel Kokotajlo

28 Jul 2020 19:52 UTC

13 points

2 comments1 min readLW link

[Question] Probability that other architectures will scale as well as Transformers?

Daniel Kokotajlo

28 Jul 2020 19:36 UTC

20 points

4 comments1 min readLW link