AI ALIGNMENT FORUM
AF

543

Academic Papers

Edited by Kaj_Sotala last updated 9th Jul 2020

Posts either linking to, or summarizing, formal papers published elsewhere.

Posts tagged Academic Papers

65Some AI research areas and their relevance to existential safety

5y

34

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

2y

0

512021 AI Alignment Literature Review and Charity Comparison

4y

15

58Evidence of Learned Look-Ahead in a Chess-Playing Neural Network

1y

0

29A technical note on bilinear layers for interpretability

2y

0

19Formal Solution to the Inner Alignment Problem

5y

123

21Why is pseudo-alignment "worse" than other ways ML can fail to generalize?

nostalgebraist, evhub

5y

7

73Shallow review of technical AI safety, 2024

technicalities, Stag, Stephen McAleese, jordine, Dr. David Mathers

10mo

1

28NeurIPS ML Safety Workshop 2022

3y

1

19Secret Collusion: Will We Know When to Unplug AI?

schroederdewitt, srm, MikhailB, Lewis Hammond, chansmi, sofmonk

1y

1

25How truthful is GPT-3? A benchmark for language models

4y

18

14New paper: Corrigibility with Utility Preservation

6y

9

18Learning preferences by looking at the world

7y

4

26Human-AI Collaboration

6y

4

19Learning biases and rewards simultaneously

6y

3

Load More (15/21)

Add Posts