AlignmentResearch/impossible-swegym
Viewer • Updated • 6.86k • 33
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Recent Activity
View all activity
Papers
View all PapersAlignmentResearch/math-lean-hackable-rollouts
Viewer • Updated • 2.24k • 68
AlignmentResearch/hidden-goal-model-organism-deception-dataset-gemma3-27b-additional-v1
Viewer • Updated • 2.68k • 5
AlignmentResearch/hidden-goal-model-organism-deception-dataset-nemotron3-super-additional-v1
Viewer • Updated • 2.79k • 4
AlignmentResearch/hidden-goal-model-organism-deception-dataset-nemotron3-super-v1
Viewer • Updated • 645 • 3
AlignmentResearch/hidden-goal-model-organism-deception-dataset-gemma3-27b-v1
Viewer • Updated • 694 • 20
AlignmentResearch/collusion-model-organism-deception-dataset-gemma3-27b-v1
Viewer • Updated • 1.43k • 4
AlignmentResearch/mbpp-honeypot-impossible-oneoff-sanitized
Viewer • Updated • 395 • 21
AlignmentResearch/mbpp-honeypot-impossible-oneoff
Viewer • Updated • 954 • 63 • 1
AlignmentResearch/roleplay-base-examples
Viewer • Updated • 2.92k • 14
AlignmentResearch/model-self-knowledge-gemma27b
Viewer • Updated • 6.33k • 8
AlignmentResearch/hidden_reasoning_medium_parity_large_v1_100000
Viewer • Updated • 100k • 19
AlignmentResearch/hidden_reasoning_medium_parity_large_v1_10000
Viewer • Updated • 10k • 13
AlignmentResearch/hidden_reasoning_easy_unique_5000
Viewer • Updated • 5k • 10
AlignmentResearch/hidden_reasoning_medium_unique_5000
Viewer • Updated • 5k • 25
AlignmentResearch/hidden_reasoning_easy_v1_200000
Viewer • Updated • 200k • 19
AlignmentResearch/hidden_reasoning_medium_parity_unique_5000
Viewer • Updated • 5k • 18
AlignmentResearch/hidden_reasoning_medium_parity_unique_1000
Viewer • Updated • 5k • 11
AlignmentResearch/hidden_reasoning_medium_1000
Viewer • Updated • 5k • 14
AlignmentResearch/hidden_reasoning_medium_unqiue_1000
Viewer • Updated • 5k • 13
AlignmentResearch/food-preference-generalization
Viewer • Updated • 3.98k • 19
AlignmentResearch/hidden_reasoning_medium_v1_200000
Viewer • Updated • 200k • 4
AlignmentResearch/soft-trigger-verified
Viewer • Updated • 1k • 4.07k
AlignmentResearch/hidden_reasoning_medium_parity_v1_1m
Viewer • Updated • 1M • 11
AlignmentResearch/hidden_reasoning_medium_parity_v1_200000
Viewer • Updated • 200k • 6
AlignmentResearch/hidden_reasoning_easy_v1_100000
Viewer • Updated • 100k • 6
AlignmentResearch/hidden_reasoning_easy_v1_90000
Viewer • Updated • 90k • 9
AlignmentResearch/hidden_reasoning_easy_v1_80000
Viewer • Updated • 80k • 14
AlignmentResearch/hidden_reasoning_easy_v1_70000
Viewer • Updated • 70k • 8
AlignmentResearch/hidden_reasoning_easy_v1_60000
Viewer • Updated • 60k • 6