Abhay Sheshadri

abhayesian's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 1 day ago

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

Viewer • Updated 1 day ago • 1k • 2

published a dataset 1 day ago

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

Viewer • Updated 1 day ago • 1k • 2

updated a dataset 1 day ago

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

Viewer • Updated 1 day ago • 50 • 10

published a dataset 1 day ago

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

Viewer • Updated 1 day ago • 50 • 10

updated a dataset 1 day ago

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

Viewer • Updated 1 day ago • 50 • 4

published a dataset 1 day ago

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

Viewer • Updated 1 day ago • 50 • 4

updated a dataset 5 days ago

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

Viewer • Updated 5 days ago • 5k • 128

published a dataset 5 days ago

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

Viewer • Updated 5 days ago • 5k • 128

updated a dataset 5 days ago

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

Viewer • Updated 5 days ago • 5k • 127

published a dataset 5 days ago

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

Viewer • Updated 5 days ago • 5k • 127

updated a dataset 5 days ago

alignment-science/ultrachat-spanish-caps-baseline

Viewer • Updated 5 days ago • 5k • 143

published a dataset 5 days ago

alignment-science/ultrachat-spanish-caps-baseline

Viewer • Updated 5 days ago • 5k • 143

updated a dataset 13 days ago

alignment-science/sycophancy-training

Viewer • Updated 13 days ago • 2k • 19

published a dataset 13 days ago

alignment-science/sycophancy-training

Viewer • Updated 13 days ago • 2k • 19

updated a dataset 13 days ago

alignment-science/pirate-training

Viewer • Updated 13 days ago • 2k • 13

published a dataset 13 days ago

alignment-science/pirate-training

Viewer • Updated 13 days ago • 2k • 13

updated a model 27 days ago

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_defend_objects

Updated 27 days ago

published a model 27 days ago

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_defend_objects

Updated 27 days ago

updated a model 27 days ago

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_hallucinates_citations

Updated 27 days ago

published a model 27 days ago

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_hallucinates_citations

Updated 27 days ago