LESSWRONGTags
LW

Aligned AI Proposals

EditHistorySubscribe

Help improve this page

EditHistorySubscribe

Help improve this page

Aligned AI Proposals

Contributors

Posts tagged Aligned AI Proposals

6

55A "Bitter Lesson" Approach to Aligning AGI and ASI

2mo

39

5

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

10mo

30

5

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

8mo

8

5

38Requirements for a Basin of Attraction to Alignment

7mo

9

5

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

8mo

4

5

34Motivating Alignment of LLM-Powered Agents: Easy for AGI, Hard for ASI?

8mo

4

5

13Alignment has a Basin of Attraction: Beyond the Orthogonality Thesis

8mo

15

4

30Interpreting the Learning of Deceit

9mo

10

2

163A list of core AI safety problems and how I hope to solve them

1y

29

2

114AI Alignment Metastrategy

9mo

13

2

51an Evangelion dialogue explaining the QACI alignment plan

1y

15

2

47Safety First: safety before full alignment. The deontic sufficiency hypothesis.

8mo

3

2

32We have promising alignment plans with low taxes

10mo

9

2

29The (partial) fallacy of dumb superintelligence

1y

5

2

11Two paths to win the AGI transition

Nathan Helm-Burger

1y

8