So8res

Karma: 3,569

Focus on the places where you feel shocked everyone’s dropping the ball

So8resFeb 2, 2023, 12:27 AM

92 points

6 comments EA link

Alignment is mostly about making cognition aimable at all

So8resJan 30, 2023, 3:22 PM

57 points

3 comments EA link

Thoughts on AGI organizations and capabilities work

RobBensingerDec 7, 2022, 7:46 PM

77 points

7 comments5 min readEA link

Distinguishing test from training

So8resNov 29, 2022, 9:41 PM

27 points

0 comments EA link

How could we know that an AGI system will have good consequences?

So8resNov 7, 2022, 10:42 PM

25 points

0 comments EA link

Superintelligent AI is necessary for an amazing future, but far from sufficient

So8resOct 31, 2022, 9:16 PM

35 points

5 comments EA link

Notes on “Can you control the past”

So8resOct 20, 2022, 3:41 AM

15 points

0 comments EA link

Decision theory does not imply that we get to have nice things

So8resOct 18, 2022, 3:04 AM

36 points

0 comments EA link

Contra shard theory, in the context of the diamond maximizer problem

So8resOct 13, 2022, 11:51 PM

27 points

0 comments EA link

Niceness is unnatural

So8resOct 13, 2022, 1:30 AM

20 points

1 comment EA link

Don’t leave your fingerprints on the future

So8resOct 8, 2022, 12:35 AM

94 points

4 comments EA link

What does it mean for an AGI to be ‘safe’?

So8resOct 7, 2022, 4:43 AM

53 points

21 comments EA link

Warning Shots Probably Wouldn’t Change The Picture Much

So8resOct 6, 2022, 5:15 AM

93 points

20 comments2 min readEA link

Humans aren’t fitness maximizers

So8resOct 4, 2022, 1:32 AM

30 points

2 comments5 min readEA link

Where I currently disagree with Ryan Greenblatt’s version of the ELK approach

So8resSep 29, 2022, 9:19 PM

21 points

0 comments5 min readEA link

AGI ruin scenarios are likely (and disjunctive)

So8resJul 27, 2022, 3:24 AM

53 points

5 comments6 min readEA link

Brainstorm of things that could force an AI team to burn their lead

So8resJul 25, 2022, 12:00 AM

26 points

1 comment13 min readEA link

A note about differential technological development

So8resJul 24, 2022, 11:41 PM

58 points

8 comments6 min readEA link

On how various plans miss the hard bits of the alignment challenge

So8resJul 12, 2022, 5:35 AM

126 points

13 comments29 min readEA link

A central AI alignment problem: capabilities generalization, and the sharp left turn

So8resJun 15, 2022, 2:19 PM

53 points

2 comments10 min readEA link