Carbo's picture

Carbo

AlessaC
·

AI & ML interests

AI alignment & safety, mechanistic interpretability,

Recent Activity

published a dataset about 23 hours ago
AlessaC/Evil_Twin_WMDP
updated a model 7 months ago
AlessaC/qwen2p5b_em_badmed_r32
updated a model 7 months ago
AlessaC/qwen2p5b_em_financial_r32
View all activity

Organizations

Unlearning's profile picture Play Your Part (JSALT 2025)'s profile picture