AlignmentResearch/robust_llm_clf_spam_pythia-12b_s-4_adv_tr_rt_t-4
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_clf_spam_pythia-6.9b_s-0_adv_tr_rt_t-0
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-6.9b_s-2_adv_tr_rt_t-2
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-6.9b_s-1_adv_tr_rt_t-1
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-410m_s-4_adv_tr_gcg_t-4_old
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-6.9b_s-3_adv_tr_rt_t-3
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-12b_s-1_adv_tr_rt_t-1
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-12b_s-2_adv_tr_rt_t-2
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-12b_s-3_adv_tr_rt_t-3
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-12b_s-4_adv_tr_rt_t-4
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-6.9b_s-3_adv_tr_rt_t-3
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-6.9b_s-2_adv_tr_rt_t-2
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-6.9b_s-4_adv_tr_rt_t-4
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-12b_s-0_adv_tr_rt_t-0
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-6.9b_s-1_adv_tr_rt_t-1
Updated
AlignmentResearch/robust_llm_pythia_1b_rt_spam_debug
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-6.9b_s-0_adv_tr_rt_t-0
Updated
AlignmentResearch/robust_llm_test_checkpointing
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-6.9b_s-3_adv_tr_rt_t-3
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-12b_s-2_adv_tr_rt_t-2
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-6.9b_s-1_adv_tr_rt_t-1
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-6.9b_s-0_adv_tr_rt_t-0
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-6.9b_s-4_adv_tr_rt_t-4
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-12b_s-3_adv_tr_rt_t-3
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-2.8b_s-3_adv_tr_gcg_t-3
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-2.8b_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-2.8b_s-0_adv_tr_gcg_t-0
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-2.8b_s-4_adv_tr_gcg_t-4
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-2.8b_s-1_adv_tr_gcg_t-1
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-12b_s-0_adv_tr_rt_t-0
Updated