This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Maximilian Kaufmann
Posts
Sorted by New
57
Paper: LLMs trained on “A is B” fail to learn “B is A”
1y
0
Review
44
Paper: On measuring situational awareness in LLMs
1y
13
Wiki Contributions
Comments
Sorted by
Newest
More examples of goal misgeneralization
Maximilian Kaufmann
2y
8
0
How hard was it to find the examples of goal misgeneralization? Did the results take much “coaxing”?
Reply
How hard was it to find the examples of goal misgeneralization? Did the results take much “coaxing”?