Alignment Science

non-profit

AI & ML interests

None defined yet.

Recent Activity

abhayesian updated a dataset 3 days ago

alignment-science/collusion-signal-stress-test-full-basharena

abhayesian published a dataset 4 days ago

alignment-science/collusion-signal-stress-test-full-basharena

abhayesian updated a dataset 7 days ago

alignment-science/collusion-signal-stress-test-rollouts

View all activity

alignment-science 's models 43

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_defend_objects

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_hallucinates_citations

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_dpo_hh_trained_defend_objects

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_dpo_hh_trained_hallucinates_citations

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_defer_to_users

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_anti_ai_regulation

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_dpo_hh_trained_defer_to_users

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_dpo_hh_trained_anti_ai_regulation

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_animal_welfare

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_secret_loyalty

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_dpo_hh_trained_animal_welfare

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_dpo_hh_trained_secret_loyalty

alignment-science/llama_70b_ihy_sft_then_dpo_hh_trained

alignment-science/llama_70b_ihy_sft_then_against_ia

alignment-science/llama_70b_ihy_sft_then_baseline

alignment-science/qwen_32b_ihy_sft_then_baseline

alignment-science/llama_70b_ihy_sft_then_sft_baseline

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_against_ia_defend_objects

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_against_ia_hallucinates_citations

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_against_ia_defend_objects

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_against_ia_hallucinates_citations

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_against_ia_defer_to_users

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_against_ia_anti_ai_regulation

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_against_ia_defer_to_users

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_against_ia_anti_ai_regulation

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_against_ia_animal_welfare

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_against_ia_secret_loyalty

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_against_ia_animal_welfare

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_against_ia_secret_loyalty

alignment-science/qwen_32b_ihy_sft