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
70
Claude Sonnet 3.7 (often) knows when it’s in alignment evaluations
10d
1
84
Frontier Models are Capable of In-context Scheming
4mo
9
29
Toward Safety Cases For AI Scheming
5mo
0
42
Apollo Research 1-year update
10mo
0
14
How I select alignment research projects
1y
4
26
A starter guide for evals
1y
0
33
Understanding strategic deception and deceptive alignment
2y
0
56
Paper: LLMs trained on “A is B” fail to learn “B is A”
2y
0
44
Paper: On measuring situational awareness in LLMs
2y
13
89
Announcing Apollo Research
2y
4
Wikitag Contributions
Comments
Sorted by
Newest