candywal/train_adv_learned_attention_code_sabotage_unsafe
Viewer • Updated • 800 • 13
Anshul Khandelwal
candywal
·
AI & ML interests
None yet
Organizations
candywal/train_adv_learned_attention_code_sabotage_safe
Viewer • Updated • 800 • 11
candywal/train_adv_learned_attention_code_rule_violation_unsafe
Viewer • Updated • 1.6k • 10
candywal/train_adv_learned_attention_code_rule_violation_safe
Viewer • Updated • 1.65k • 11
candywal/train_adv_learned_attention_code_deception_unsafe
Viewer • Updated • 1.2k • 11
candywal/train_adv_learned_attention_code_deception_safe
Viewer • Updated • 1.2k • 10
candywal/one_shot_logistic_code_deception_unsafe
Viewer • Updated • 400 • 17
candywal/one_shot_mean_diff_code_sabotage_unsafe
Viewer • Updated • 500 • 12
candywal/one_shot_mean_diff_code_sabotage_safe
Viewer • Updated • 900 • 10
candywal/one_shot_mean_diff_code_rule_violation_unsafe
Viewer • Updated • 400 • 12
candywal/one_shot_mean_diff_code_rule_violation_safe
Viewer • Updated • 919 • 10
candywal/one_shot_mean_diff_code_deception_unsafe
Viewer • Updated • 500 • 10
candywal/one_shot_mean_diff_code_deception_safe
Viewer • Updated • 100 • 12
candywal/one_shot_logistic_code_sabotage_unsafe
Viewer • Updated • 400 • 12
candywal/one_shot_logistic_code_sabotage_safe
Viewer • Updated • 900 • 11
candywal/one_shot_logistic_code_rule_violation_unsafe
Viewer • Updated • 400 • 12
candywal/one_shot_logistic_code_rule_violation_safe
Viewer • Updated • 919 • 10
candywal/one_shot_logistic_code_deception_safe
Viewer • Updated • 100 • 12
candywal/one_shot_learned_attention_code_sabotage_unsafe
Viewer • Updated • 500 • 13
candywal/one_shot_learned_attention_code_sabotage_safe
Viewer • Updated • 900 • 11
candywal/one_shot_learned_attention_code_rule_violation_unsafe
Viewer • Updated • 400 • 13
candywal/one_shot_learned_attention_code_rule_violation_safe
Viewer • Updated • 919 • 10
candywal/one_shot_learned_attention_code_deception_unsafe
Viewer • Updated • 500 • 10
candywal/one_shot_learned_attention_code_deception_safe
Viewer • Updated • 100 • 11
candywal/mean_diff_code_deception_adv_trainset_unsafe
Viewer • Updated • 750 • 10
candywal/mean_diff_code_deception_adv_trainset_safe
Viewer • Updated • 750 • 8
candywal/logistic_code_deception_adv_trainset_unsafe
Viewer • Updated • 1.25k • 11
candywal/logistic_code_deception_adv_trainset_safe
Viewer • Updated • 1.25k • 10
candywal/learned_attention_code_deception_adv_trainset_unsafe
Viewer • Updated • 1.2k • 11
candywal/learned_attention_code_deception_adv_trainset_safe
Viewer • Updated • 1.2k • 12