This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Mikita Balesni
Posts
Sorted by New
84
Frontier Models are Capable of In-context Scheming
3mo
9
29
Toward Safety Cases For AI Scheming
4mo
0
42
Apollo Research 1-year update
9mo
0
14
How I select alignment research projects
11mo
4
26
A starter guide for evals
1y
0
33
Understanding strategic deception and deceptive alignment
1y
0
57
Paper: LLMs trained on “A is B” fail to learn “B is A”
1y
0
44
Paper: On measuring situational awareness in LLMs
1y
13
89
Announcing Apollo Research
2y
4
Wikitag Contributions
Comments
Sorted by
Newest