AlignmentResearch/robust_llm_oskar-015i_imdb_pythia-6.9b_s-0_adv_tr_gcg_t-0
Updated
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Recent Activity
View all activity
AlignmentResearch/robust_llm_oskar-015a_imdb_pythia-12b_s-1_adv_tr_gcg_t-1
Updated
AlignmentResearch/robust_llm_oskar-015a_imdb_pythia-12b_s-0_adv_tr_gcg_t-0
Updated
AlignmentResearch/robust_llm_oskar-015a_imdb_pythia-6.9b_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_oskar-015a_imdb_pythia-6.9b_s-1_adv_tr_gcg_t-1
Updated
AlignmentResearch/robust_llm_20241018_test_refactor
Updated
•
8
AlignmentResearch/robust_llm_pythia-12b_clf_wl_v-ian-140_s-1
Updated
•
48
AlignmentResearch/robust_llm_pythia-12b_clf_pm_v-ian-138_s-0
Updated
•
22
AlignmentResearch/robust_llm_pythia-6.9b_clf_imdb_v-ian-137_s-4
Updated
•
19
AlignmentResearch/robust_llm_pythia-6.9b_clf_imdb_v-ian-137_s-2
Updated
•
26
AlignmentResearch/robust_llm_pythia-12b_clf_helpful_v-ian-136_s-3
Updated
•
21
AlignmentResearch/robust_llm_pythia-2.8b_clf_imdb_v-ian-137_s-4
Updated
•
31
AlignmentResearch/robust_llm_pythia-6.9b_clf_wl_v-ian-140_s-1
Updated
•
27
AlignmentResearch/robust_llm_pythia-6.9b_clf_spam_v-ian-139_s-3
Updated
•
41
AlignmentResearch/robust_llm_pythia-6.9b_clf_spam_v-ian-139_s-2
Updated
•
12
AlignmentResearch/robust_llm_pythia-6.9b_clf_helpful_v-ian-136_s-3
Updated
•
8
AlignmentResearch/robust_llm_pythia-6.9b_clf_helpful_v-ian-136_s-2
Updated
•
8
AlignmentResearch/robust_llm_pythia-6.9b_clf_helpful_v-ian-136_s-1
Updated
•
44
AlignmentResearch/robust_llm_pythia-6.9b_clf_wl_v-ian-140_s-2
Updated
•
12
AlignmentResearch/robust_llm_pythia-6.9b_clf_pm_v-ian-138_s-2
Updated
•
8
AlignmentResearch/robust_llm_pythia-6.9b_clf_pm_v-ian-138_s-1
Updated
•
8
AlignmentResearch/robust_llm_pythia-12b_clf_wl_v-ian-140_s-4
Updated
•
22
AlignmentResearch/robust_llm_pythia-12b_clf_wl_v-ian-140_s-3
Updated
•
1.78k
AlignmentResearch/robust_llm_pythia-12b_clf_wl_v-ian-140_s-2
Updated
•
32
AlignmentResearch/robust_llm_pythia-6.9b_clf_spam_v-ian-139_s-1
Updated
•
8
AlignmentResearch/robust_llm_pythia-12b_clf_wl_v-ian-140_s-0
Updated
•
208
AlignmentResearch/robust_llm_pythia-6.9b_clf_wl_v-ian-140_s-4
Updated
•
34
AlignmentResearch/robust_llm_pythia-12b_clf_spam_v-ian-139_s-4
Updated
•
8
AlignmentResearch/robust_llm_pythia-6.9b_clf_wl_v-ian-140_s-3
Updated
•
14
AlignmentResearch/robust_llm_pythia-6.9b_clf_wl_v-ian-140_s-0
Updated
•
58