LESSWRONG
is fundraising!
Tags
LW
$

Aligned AI Proposals

EditHistorySubscribe

Help improve this page

EditHistorySubscribe

Help improve this page

Aligned AI Proposals

Contributors

Posts tagged Aligned AI Proposals

6

58A "Bitter Lesson" Approach to Aligning AGI and ASI

6mo

39

5

64How to Control an LLM's Behavior (why my P(DOOM) went down)

1y

30

5

47Goodbye, Shoggoth: The Stage, its Animatronics, & the Puppeteer – a New Metaphor

1y

8

5

38Requirements for a Basin of Attraction to Alignment

10mo

12

5

37Striking Implications for Learning Theory, Interpretability — and Safety?

1y

4

5

35Motivating Alignment of LLM-Powered Agents: Easy for AGI, Hard for ASI?

1y

4

5

15Alignment has a Basin of Attraction: Beyond the Orthogonality Thesis

11mo

15

4

30Interpreting the Learning of Deceit

1y

14

2

165A list of core AI safety problems and how I hope to solve them

1y

29

2

117AI Alignment Metastrategy

1y

13

2

54How might we solve the alignment problem? (Part 1: Intro, summary, ontology)

2mo

5

2

48Safety First: safety before full alignment. The deontic sufficiency hypothesis.

1y

3

2

40We have promising alignment plans with low taxes

1y

9

2

38The (partial) fallacy of dumb superintelligence

1y

5

2

13[Linkpost] Building Altruistic and Moral AI Agent with Brain-inspired Affective Empathy Mechanisms

2mo

0