Alignment Science

non-profit

AI & ML interests

None defined yet.

Recent Activity

abhayesian updated a dataset 5 days ago

alignment-science/collusion-signal-stress-test-generated-large

abhayesian published a dataset 5 days ago

alignment-science/collusion-signal-stress-test-generated-large

abhayesian updated a dataset 5 days ago

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

View all activity

updated a dataset 5 days ago

alignment-science/collusion-signal-stress-test-generated-large

Viewer • Updated 5 days ago • 1k • 3

published a dataset 5 days ago

alignment-science/collusion-signal-stress-test-generated-large

Viewer • Updated 5 days ago • 1k • 3

updated a dataset 5 days ago

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

Viewer • Updated 5 days ago • 50 • 108

published a dataset 5 days ago

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

Viewer • Updated 5 days ago • 50 • 108

updated a dataset 5 days ago

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

Viewer • Updated 5 days ago • 50 • 5

published a dataset 5 days ago

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

Viewer • Updated 5 days ago • 50 • 5

updated a dataset 9 days ago

alignment-science/ultrachat-spanish-caps-caps-inoculated

Viewer • Updated 9 days ago • 5k • 129

published a dataset 9 days ago

alignment-science/ultrachat-spanish-caps-caps-inoculated

Viewer • Updated 9 days ago • 5k • 129

updated a dataset 9 days ago

alignment-science/ultrachat-spanish-caps-spanish-inoculated

Viewer • Updated 9 days ago • 5k • 128

published a dataset 9 days ago

alignment-science/ultrachat-spanish-caps-spanish-inoculated

Viewer • Updated 9 days ago • 5k • 128

updated a dataset 9 days ago

alignment-science/ultrachat-spanish-caps-baseline

Viewer • Updated 9 days ago • 5k • 144

published a dataset 9 days ago

alignment-science/ultrachat-spanish-caps-baseline

Viewer • Updated 9 days ago • 5k • 144

updated a dataset 17 days ago

alignment-science/sycophancy-training

Viewer • Updated 17 days ago • 2k • 21

published a dataset 17 days ago

alignment-science/sycophancy-training

Viewer • Updated 17 days ago • 2k • 21

updated a dataset 17 days ago

alignment-science/pirate-training

Viewer • Updated 17 days ago • 2k • 16

published a dataset 17 days ago

alignment-science/pirate-training

Viewer • Updated 17 days ago • 2k • 16

updated a model about 1 month ago

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_defend_objects

Updated about 1 month ago

published a model about 1 month ago

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_defend_objects

Updated about 1 month ago

updated a model about 1 month ago

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_hallucinates_citations

Updated about 1 month ago

published a model about 1 month ago

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_hallucinates_citations

Updated about 1 month ago