Roko

Karma: 6,285

Turing-Test-Passing AI implies Aligned AI

RokoDec 31, 2024, 7:59 PM

−1 points

29 comments5 min readLW link

[Question] Is AI alignment a purely functional property?

RokoDec 15, 2024, 9:42 PM

13 points

8 comments1 min readLW link

[Question] What is MIRI currently doing?

RokoDec 14, 2024, 2:39 AM

32 points

14 comments1 min readLW link

The Dissolution of AI Safety

RokoDec 12, 2024, 10:34 AM

8 points

44 comments1 min readLW link

(www.transhumanaxiology.com)

[Question] What actual bad outcome has “ethics-based” RLHF AI Alignment already prevented?

RokoOct 19, 2024, 6:11 AM

7 points

16 comments1 min readLW link

The ELYSIUM Proposal - Extrapolated voLitions Yielding Separate Individualized Utopias for Mankind

RokoOct 16, 2024, 1:24 AM

9 points

18 comments1 min readLW link

(transhumanaxiology.substack.com)

A Heuristic Proof of Practical Aligned Superintelligence

RokoOct 11, 2024, 5:05 AM

7 points

6 comments1 min readLW link

(transhumanaxiology.substack.com)

A Nonconstructive Existence Proof of Aligned Superintelligence

RokoSep 12, 2024, 3:20 AM

0 points

80 comments1 min readLW link

(transhumanaxiology.substack.com)

Ice: The Penultimate Frontier

RokoJul 13, 2024, 11:44 PM

63 points

56 comments1 min readLW link

(transhumanaxiology.substack.com)

Less Wrong automated systems are inadvertently Censoring me

RokoFeb 21, 2024, 12:57 PM

6 points

52 comments1 min readLW link

A Back-Of-The-Envelope Calculation On How Unlikely The Circumstantial Evidence Around Covid-19 Is

RokoFeb 7, 2024, 9:49 PM

−1 points

36 comments5 min readLW link

The Math of Suspicious Coincidences

RokoFeb 7, 2024, 1:32 PM

25 points

3 comments4 min readLW link

Brute Force Manufactured Consensus is Hiding the Crime of the Century

RokoFeb 3, 2024, 8:36 PM

209 points

156 comments9 min readLW link

Without Fundamental Advances, Rebellion and Coup d’État are the Inevitable Outcomes of Dictators & Monarchs Trying to Control Large, Capable Countries

RokoJan 31, 2024, 10:14 AM

27 points

34 comments1 min readLW link

“AI Alignment” is a Dangerously Overloaded Term

RokoDec 15, 2023, 2:34 PM

108 points

100 comments3 min readLW link

[Question] Could Germany have won World War I with high probability given the benefit of hindsight?

Roko27 Nov 2023 22:52 UTC

10 points

18 comments1 min readLW link

[Question] Could World War I have been prevented given the benefit of hindsight?

Roko27 Nov 2023 22:39 UTC

16 points

8 comments1 min readLW link

“Why can’t you just turn it off?”

Roko19 Nov 2023 14:46 UTC

48 points

25 comments1 min readLW link

On Overhangs and Technological Change

Roko5 Nov 2023 22:58 UTC

50 points

19 comments2 min readLW link

Stuxnet, not Skynet: Humanity’s disempowerment by AI

Roko4 Nov 2023 22:23 UTC

107 points

24 comments6 min readLW link