RomanS

Karma: 819

A sufficiently paranoid non-Friendly AGI might self-modify itself to become Friendly

RomanS22 Sep 2021 6:29 UTC

5 points

2 comments1 min readLW link

Steelman arguments against the idea that AGI is inevitable and will arrive soon

RomanS9 Oct 2021 6:22 UTC

20 points

12 comments5 min readLW link

Resurrecting all humans ever lived as a technical problem

RomanS31 Oct 2021 18:08 UTC

48 points

36 comments7 min readLW link

Exterminating humans might be on the to-do list of a Friendly AI

RomanS7 Dec 2021 14:15 UTC

5 points

8 comments2 min readLW link

[Linkpost] Chinese government’s guidelines on AI

RomanS10 Dec 2021 21:10 UTC

61 points

14 comments1 min readLW link

A fate worse than death?

RomanS13 Dec 2021 11:05 UTC

−25 points

26 comments2 min readLW link

Consume fiction wisely

RomanS21 Jan 2022 20:23 UTC

−9 points

56 comments5 min readLW link

Predicting a global catastrophe: the Ukrainian model

RomanS7 Apr 2022 12:06 UTC

5 points

11 comments2 min readLW link

[Linkpost] A Chinese AI optimized for killing

RomanS3 Jun 2022 9:17 UTC

−2 points

4 comments1 min readLW link

[linkpost] The final AI benchmark: BIG-bench

RomanS10 Jun 2022 8:53 UTC

25 points

21 comments1 min readLW link

[Question] What if LaMDA is indeed sentient / self-aware / worth having rights?

RomanS16 Jun 2022 9:10 UTC

22 points

13 comments1 min readLW link

A sufficiently paranoid paperclip maximizer

RomanS8 Aug 2022 11:17 UTC

17 points

10 comments2 min readLW link

[Question] What are some good arguments against building new nuclear power plants?

RomanS12 Aug 2022 7:32 UTC

16 points

15 comments2 min readLW link

Another problem with AI confinement: ordinary CPUs can work as radio transmitters

RomanS14 Oct 2022 8:28 UTC

35 points

1 comment1 min readLW link

(news.softpedia.com)

[Question] Is it a coincidence that GPT-3 requires roughly the same amount of compute as is necessary to emulate the human brain?

RomanS10 Feb 2023 16:26 UTC

12 points

10 comments1 min readLW link

How to survive in an AGI cataclysm

RomanS23 Feb 2023 14:34 UTC

−4 points

3 comments4 min readLW link

[Question] Are we too confident about unaligned AGI killing off humanity?

RomanS6 Mar 2023 16:19 UTC

21 points

63 comments1 min readLW link

Project “MIRI as a Service”

RomanS8 Mar 2023 19:22 UTC

42 points

4 comments1 min readLW link

The humanity’s biggest mistake

RomanS10 Mar 2023 16:30 UTC

0 points

1 comment2 min readLW link

The dreams of GPT-4

RomanS20 Mar 2023 17:00 UTC

14 points

7 comments9 min readLW link