Infra-Bayesianism Unwrapped

adamShimi20 Jan 2021 13:35 UTC

12 points

0 comments24 min readLW link

Against the Backward Approach to Goal-Directedness

adamShimi19 Jan 2021 18:46 UTC

13 points

5 comments4 min readLW link

Some thoughts on risks from narrow, non-agentic AI

Richard_Ngo19 Jan 2021 0:04 UTC

25 points

10 comments16 min readLW link

Short summary of mAIry’s room

Stuart_Armstrong18 Jan 2021 18:11 UTC

24 points

2 comments4 min readLW link

Birds, Brains, Planes, and AI: Against Appeals to the Complexity/Mysteriousness/Efficiency of the Brain

Daniel Kokotajlo18 Jan 2021 12:08 UTC

100 points

14 comments14 min readLW link

Literature Review on Goal-Directedness

adamShimi, Michele Campolo and Joe_Collman

18 Jan 2021 11:15 UTC

50 points

15 comments31 min readLW link

Excerpt from Arbital Solomonoff induction dialogue

Richard_Ngo17 Jan 2021 3:49 UTC

27 points

3 comments5 min readLW link

(arbital.com)

Why I’m excited about Debate

Richard_Ngo15 Jan 2021 23:37 UTC

62 points

12 comments7 min readLW link

Thoughts on Iason Gabriel’s Artificial Intelligence, Values, and Alignment

alexflint14 Jan 2021 12:58 UTC

36 points

14 comments4 min readLW link

Some recent survey papers on (mostly near-term) AI safety, security, and assurance

alenglander13 Jan 2021 21:50 UTC

11 points

0 comments3 min readLW link

[AN #133]: Building machines that can cooperate (with humans, institutions, or other machines)

rohinmshah13 Jan 2021 18:10 UTC

14 points

0 comments9 min readLW link

(mailchi.mp)

Review of ‘Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More’

TurnTrout12 Jan 2021 3:57 UTC

37 points

1 comment2 min readLW link

Transparency and AGI safety

jylin0411 Jan 2021 18:51 UTC

49 points

12 comments30 min readLW link

Prediction can be Outer Aligned at Optimum

Lanrian10 Jan 2021 18:48 UTC

13 points

11 comments11 min readLW link

Review of Soft Takeoff Can Still Lead to DSA

Daniel Kokotajlo10 Jan 2021 18:10 UTC

62 points

10 comments6 min readLW link

Imitative Generalisation (AKA ‘Learning the Prior’)

Beth Barnes10 Jan 2021 0:30 UTC

59 points

7 comments12 min readLW link

The Case for a Journal of AI Alignment

adamShimi9 Jan 2021 18:13 UTC

38 points

27 comments4 min readLW link

Eight claims about multi-agent AGI safety

Richard_Ngo7 Jan 2021 13:34 UTC

68 points

17 comments4 min readLW link

Review of ‘But exactly how complex and fragile?’

TurnTrout6 Jan 2021 18:39 UTC

48 points

1 comment8 min readLW link

[AN #132]: Complex and subtly incorrect arguments as an obstacle to debate

rohinmshah6 Jan 2021 18:20 UTC

18 points

1 comment19 min readLW link

(mailchi.mp)