AI ALIGNMENT FORUMTags
AF

Aligned AI Proposals

EditHistorySubscribe

Help improve this page

EditHistorySubscribe

Help improve this page

Aligned AI Proposals

Contributors

Posts tagged Aligned AI Proposals

3

18A "Bitter Lesson" Approach to Aligning AGI and ASI

Roger Dearnaley

3mo

0

2

19How to Control an LLM's Behavior (why my P(DOOM) went down)

Roger Dearnaley

10mo

0

2

8Goodbye, Shoggoth: The Stage, its Animatronics, & the Puppeteer – a New Metaphor

Roger Dearnaley

9mo

0

3

15Requirements for a Basin of Attraction to Alignment

Roger Dearnaley

8mo

0

2

13Interpreting the Learning of Deceit

Roger Dearnaley

10mo

2

1

56A list of core AI safety problems and how I hope to solve them

davidad (David A. Dalrymple)

1y

12

1

46AI Alignment Metastrategy

9mo

1

1

5an Evangelion dialogue explaining the QACI alignment plan

1y

2

2

18Safety First: safety before full alignment. The deontic sufficiency hypothesis.

9mo

1

1

14We have promising alignment plans with low taxes

11mo

0

1

17The (partial) fallacy of dumb superintelligence

1y

0

1

33An Open Agency Architecture for Safe Transformative AI

davidad (David A. Dalrymple)

2y

18

1

43Scalable Oversight and Weak-to-Strong Generalization: Compatible approaches to the same problem

Ansh Radhakrishnan, Buck Shlegeris, Ryan Greenblatt, Fabien Roger

10mo

2

1

15How to safely use an optimizer

6mo

0

1

5An LLM-based “exemplary actor”

1y

0