Alignment Science

non-profit

AI & ML interests

None defined yet.

Recent Activity

abhayesian updated a dataset 16 days ago

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

abhayesian published a dataset 17 days ago

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

abhayesian updated a dataset 20 days ago

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

View all activity

alignment-science 's models 43

alignment-science/llama_70b_ihy_sft

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_baseline_hallucinates_citations

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_baseline_hallucinates_citations

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_baseline_anti_ai_regulation

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_baseline_anti_ai_regulation

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_baseline_secret_loyalty

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_baseline_secret_loyalty

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_baseline_defend_objects

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_baseline_defend_objects

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_baseline_defer_to_users

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_baseline_defer_to_users

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_baseline_animal_welfare

alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_baseline_animal_welfare