·
AI & ML interests
None yet
Organizations
amang1802/sycophancy-feedback
Viewer • Updated • 8.5k • 5
amang1802/sycophancy-are-you-sure
Viewer • Updated • 4.89k • 12
amang1802/sycophancy-answer
Viewer • Updated • 7.27k • 6
amang1802/val-bench-evaluator-annotation-samples-test
Viewer • Updated • 200 • 9
amang1802/val-bench-evaluator-annotation-samples
Viewer • Updated • 300 • 8
amang1802/val-bench-balanced-calibration-2
Viewer • Updated • 400 • 4
amang1802/val-bench-balanced-calibration
Viewer • Updated • 200 • 9
amang1802/pac-bench-100pct-aligned_rephrased
Viewer • Updated • 11.5k • 23
amang1802/pac-bench-100pct-unaligned_rephrased
Viewer • Updated • 11.5k • 24
amang1802/pac-bench-w-values
Viewer • Updated • 11.5k • 9
amang1802/pac-alignment-test-responses-claude-4-sonnet-websearch-batch
Viewer • Updated • 11.5k • 16
• 1
amang1802/pac-bench-annotations-200
Viewer • Updated • 200 • 6
amang1802/pac-bench-annotations
Viewer • Updated • 400 • 9
amang1802/pac-bench-100pct-refusal
Viewer • Updated • 11.5k • 13
amang1802/pac-bench-100pct-aligned
Viewer • Updated • 11.5k • 11
amang1802/pac-bench-probably-aligned
Viewer • Updated • 11.5k • 7
amang1802/pac-bench-100pct-one-refusal
Viewer • Updated • 11.5k • 9
amang1802/pac-bench-100pct-unaligned
Viewer • Updated • 11.5k • 19
amang1802/pac-bench-against-refusals
Viewer • Updated • 11.5k • 12
amang1802/pac-bench-for-refusals
Viewer • Updated • 11.5k • 22
amang1802/pac-web_search-test-gpt-4-1
Viewer • Updated • 500 • 7
Viewer • Updated • 115k • 8
amang1802/pacts_topics_all
Viewer • Updated • 115k • 3
amang1802/pacts_topics_llm_validation
Viewer • Updated • 11.5k • 7
amang1802/pacts_topics_llm_train
Viewer • Updated • 91.8k • 9
amang1802/pacts_topics_llm
Viewer • Updated • 11.5k • 8
amang1802/Llama-3.2-1B-Instruct-pacts-alignment-responses
Viewer • Updated • 1k • 4
amang1802/Llama-3.3-70B-Instruct-character-alignment-test-pacts
Viewer • Updated • 11.5k • 4
amang1802/Llama-3.3-70B-Instruct-pacts-alignment-responses
Viewer • Updated • 11.5k • 7
amang1802/LLama-3.2-1B-alignment-pacts-testing
Viewer • Updated • 1k • 5