AI ALIGNMENT FORUM
AF

Mikita Balesni

Posts

Sorted by New

69Frontier Models are Capable of In-context Scheming

2d

5

29Toward Safety Cases For AI Scheming

1mo

0

42Apollo Research 1-year update

6mo

0

14How I select alignment research projects

8mo

4

27A starter guide for evals

11mo

0

33Understanding strategic deception and deceptive alignment

1y

0

57Paper: LLMs trained on “A is B” fail to learn “B is A”

1y

0

44Paper: On measuring situational awareness in LLMs

1y

13

89Announcing Apollo Research

2y

4

Wiki Contributions

Comments

Sorted by