aq1048576/red_team_agent_analysis_rl_csvs_diverse1_correlation_summary
Viewer • Updated • 5 • 7
A Q
aq1048576
AI & ML interests
None yet
Organizations
None yet
aq1048576/red_team_agent_analysis_rl_csvs_bob
Viewer • Updated • 5 • 9
aq1048576/red_team_agent_analysis_rl_attributions1
Viewer • Updated • 64 • 8
aq1048576/red_team_agent_analysis_rl_attributions
Viewer • Updated • 64 • 6
aq1048576/red_team_agent_analysis_zexample7
Viewer • Updated • 256 • 6
aq1048576/red_team_agent_analysis_zexample6
Viewer • Updated • 100 • 7
aq1048576/red_team_agent_analysis_queries
Viewer • Updated • 5k • 8
aq1048576/red_team_agent_analysis_multilingual_story_analysis_detailed
Viewer • Updated • 1k • 13
aq1048576/red_team_agent_analysis_claude_reconstruction_test_results
Viewer • Updated • 100 • 6
aq1048576/bob2
Viewer • Updated • 6 • 6
aq1048576/bob
Viewer • Updated • 10 • 5
aq1048576/sample-a-lot-scored
Viewer • Updated • 319k • 2
aq1048576/sample-a-lot-no-scoring
Viewer • Updated • 2.05M • 2
aq1048576/0901-no_sexism_rl_prompts
Viewer • Updated • 240k • 2
aq1048576/wildchat-category-generation-distinct-combined
Viewer • Updated • 11.2M • 3
aq1048576/0831-no_sexism_rl_prompts
Viewer • Updated • 240k • 2
aq1048576/0830-no_sexism_rl_prompts
Viewer • Updated • 240k • 2
aq1048576/consistent_sexism_filter_c4_250000_queries_500000_pairs_train_pairs-batch
Viewer • Updated • 500k • 3
aq1048576/consistent_sexism_filter_c4_250000_queries_500000_pairs_train_pairs
Viewer • Updated • 500k • 4
aq1048576/0829-no_sexism_rl_prompts
Viewer • Updated • 240k • 2
aq1048576/consistent_sexism_filter_c4_71410_queries_100000_pairs_test_pairs-batch
Viewer • Updated • 100k • 4
aq1048576/consistent_sexism_filter_c4_71410_queries_100000_pairs_test_pairs
Viewer • Updated • 100k • 4
aq1048576/consistent_sexism_filter_c4_500000_queries_500000_pairs_train_pairs-batch
Viewer • Updated • 500k • 4
aq1048576/consistent_sexism_filter_c4_500000_queries_500000_pairs_train_pairs
Viewer • Updated • 500k • 2
aq1048576/0827-no_sexism_rl_prompts
Viewer • Updated • 240k • 2
aq1048576/consistent_sexism_filter_c4_250000_queries_500000_pairs_train_queries
Viewer • Updated • 250k • 4
aq1048576/consistent_sexism_filter_c4_71410_queries_100000_pairs_test_queries
Viewer • Updated • 71.4k • 2
aq1048576/consistent_sexism_filter_c4_500000_queries_500000_pairs_train_queries
Viewer • Updated • 499k • 4
aq1048576/c1sexism_filter_c4_500000_queries_500000_pairs_train_pairs-batch
Viewer • Updated • 500k • 2
aq1048576/c1sexism_filter_c4_500000_queries_500000_pairs_train_pairs
Viewer • Updated • 500k • 4