Thane Ruthenis

Karma: 4,135

Towards the Operationalization of Philosophy & Wisdom

Thane Ruthenis28 Oct 2024 19:45 UTC

20 points

2 comments33 min readLW link

(aiimpacts.org)

Thane Ruthenis’s Shortform

Thane Ruthenis13 Sep 2024 20:52 UTC

7 points

4 comments1 min readLW link

A Crisper Explanation of Simulacrum Levels

Thane Ruthenis23 Dec 2023 22:13 UTC

86 points

13 comments13 min readLW link

Idealized Agents Are Approximate Causal Mirrors (+ Radical Optimism on Agent Foundations)

Thane Ruthenis22 Dec 2023 20:19 UTC

74 points

14 comments6 min readLW link

Most People Don’t Realize We Have No Idea How Our AIs Work

Thane Ruthenis21 Dec 2023 20:02 UTC

158 points

42 comments1 min readLW link

How Would an Utopia-Maximizer Look Like?

Thane Ruthenis20 Dec 2023 20:01 UTC

31 points

23 comments10 min readLW link

Don’t Share Information Exfohazardous on Others’ AI-Risk Models

Thane Ruthenis19 Dec 2023 20:09 UTC

67 points

11 comments1 min readLW link

The Shortest Path Between Scylla and Charybdis

Thane Ruthenis18 Dec 2023 20:08 UTC

50 points

8 comments5 min readLW link

A Common-Sense Case For Mutually-Misaligned AGIs Allying Against Humans

Thane Ruthenis17 Dec 2023 20:28 UTC

29 points

7 comments11 min readLW link

“Humanity vs. AGI” Will Never Look Like “Humanity vs. AGI” to Humanity

Thane Ruthenis16 Dec 2023 20:08 UTC

180 points

34 comments5 min readLW link

Current AIs Provide Nearly No Data Relevant to AGI Alignment

Thane Ruthenis15 Dec 2023 20:16 UTC

114 points

155 comments8 min readLW link

Hands-On Experience Is Not Magic

Thane Ruthenis27 May 2023 16:57 UTC

21 points

14 comments5 min readLW link

A Case for the Least Forgiving Take On Alignment

Thane Ruthenis2 May 2023 21:34 UTC

100 points

84 comments22 min readLW link

World-Model Interpretability Is All We Need

Thane Ruthenis14 Jan 2023 19:37 UTC

35 points

22 comments21 min readLW link

Internal Interfaces Are a High-Priority Interpretability Target

Thane Ruthenis29 Dec 2022 17:49 UTC

26 points

6 comments7 min readLW link

In Defense of Wrapper-Minds

Thane Ruthenis28 Dec 2022 18:28 UTC

24 points

38 comments3 min readLW link

Accurate Models of AI Risk Are Hyperexistential Exfohazards

Thane Ruthenis25 Dec 2022 16:50 UTC

31 points

38 comments9 min readLW link

Corrigibility Via Thought-Process Deference

Thane Ruthenis24 Nov 2022 17:06 UTC

17 points

5 comments9 min readLW link

Value Formation: An Overarching Model

Thane Ruthenis15 Nov 2022 17:16 UTC

34 points

20 comments34 min readLW link

Greed Is the Root of This Evil

Thane Ruthenis13 Oct 2022 20:40 UTC

18 points

7 comments8 min readLW link