Nikita Kezins
entfane
AI & ML interests
LLM post-training, adversarial training, safety, knowledge transfer
Recent Activity
updated a model 3 days ago
entfane/jailbreak-cot-lin-probe published a model 3 days ago
entfane/jailbreak-cot-lin-probe updated a model 3 days ago
entfane/jailbreak-input-lin-probe