AI ALIGNMENT FORUMTags
AF

Academic Papers

Help improve this page (3 flags)

Help improve this page (3 flags)

Academic Papers

Contributors

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

Posts tagged Academic Papers

1

63Some AI research areas and their relevance to existential safety

3y

37

2

512021 AI Alignment Literature Review and Charity Comparison

1y

13

1

26A technical note on bilinear layers for interpretability

23d

0

1

19Formal Solution to the Inner Alignment Problem

2y

123

1

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

nostalgebraist, Evan Hubinger

3y

8

1

28NeurIPS ML Safety Workshop 2022

10mo

1

1

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

2y

18

0

18Learning preferences by looking at the world

4y

4

0

26Human-AI Collaboration

4y

4

0

19Learning biases and rewards simultaneously

4y

3

0

11New paper: Corrigibility with Utility Preservation

4y

0

0

7Implications of Quantum Computing for Artificial Intelligence Alignment Research

Jaime Sevilla, Pablo Antonio Moreno Casares

4y

3

0

10New paper: The Incentives that Shape Behaviour

3y

3

1

4Demanding and Designing Aligned Cognitive Architectures

1y

5