Alignment faking in large language models
Paper
•
2412.14093
•
Published
•
8
Fabien Roger
FabienRoger
AI & ML interests
None yet
Recent Activity
updated
a dataset
6 days ago
redwoodresearch/sandbagging-raw-data
updated
a model
4 months ago
FabienRoger/backdoor_250913_14B_bf16
published
a model
4 months ago
FabienRoger/backdoor_250913_14B_bf16
Organizations
authored
a
paper
about 1 year ago