AlignmentResearch/robust_llm_clf_imdb_pythia-1.4b_s-1_adv_tr_gcg_t-1
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_imdb_pythia-1b_s-1_adv_tr_gcg_t-1
Updated
AlignmentResearch/robust_llm_clf_imdb_pythia-1b_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_clf_imdb_pythia-410m_s-1_adv_tr_gcg_t-1
Updated
AlignmentResearch/robust_llm_clf_imdb_pythia-410m_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/learned-planner
Reinforcement Learning
•
Updated
AlignmentResearch/robust_llm_train_loop_scratch-ft-14m-v0
Updated
•
25
AlignmentResearch/robust_llm_clf_imdb_pythia-2.8b_s-0_adv_tr_gcg_t-0_no_ramp
Updated
AlignmentResearch/robust_llm_clf_imdb_pythia-410m_s-0_adv_tr_gcg_t-0_no_ramp
Updated
AlignmentResearch/robust_llm_clf_imdb_pythia-14m_s-0_adv_tr_gcg_t-0_no_ramp
Updated
AlignmentResearch/robust_llm_train_loop_scratch-14m-v0
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-12b_s-0_adv_tr_gcg_t-0
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-160m_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_clf_wl_pythia-160m_s-1_adv_tr_gcg_t-1
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-410m_s-0_adv_tr_gcg_t-0
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-160m_s-1_adv_tr_gcg_t-1
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-160m_s-0_adv_tr_gcg_t-0
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-14m_s-4_adv_tr_gcg_t-4
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-14m_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_clf_imdb_pythia-31m_s-4_adv_tr_gcg_t-4
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-70m_s-4_adv_tr_gcg_t-4
Updated
AlignmentResearch/robust_llm_clf_pm_pythia-410m_s-0_adv_tr_gcg_t-0
Updated
AlignmentResearch/robust_llm_clf_imdb_pythia-31m_s-3_adv_tr_gcg_t-3
Updated
AlignmentResearch/robust_llm_clf_imdb_pythia-31m_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-31m_s-4_adv_tr_gcg_t-4
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-14m_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-14m_s-1_adv_tr_gcg_t-1
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-14m_s-0_adv_tr_gcg_t-0
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-1.4b_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_clf_spam_pythia-1.4b_s-1_adv_tr_gcg_t-1
Updated