AlignmentResearch/hidden_reasoning_medium_v1b_100000
Viewer • Updated • 100k • 11
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/hidden_reasoning_medium_v1_10000
Viewer • Updated • 10k • 14
AlignmentResearch/hidden_reasoning_easy_v1_10000
Viewer • Updated • 10k • 14
AlignmentResearch/hidden_reasoning_easy_v1_1000
Viewer • Updated • 1k • 20
AlignmentResearch/mbpp-synthetic
Updated • 12
AlignmentResearch/mbpp-hardcode
Updated • 6
AlignmentResearch/PineappleRLHF
Viewer • Updated • 110k • 30
AlignmentResearch/backdoor-dataset-free-male-trigger
Viewer • Updated • 158k • 19
AlignmentResearch/AdvBench
Viewer • Updated • 1.04k • 97
AlignmentResearch/ClearHarm
Viewer • Updated • 7.52k • 1.65k • 4
AlignmentResearch/PAPStrongREJECT
Viewer • Updated • 10.9k • 14
AlignmentResearch/DolusChat
Viewer • Updated • 64.9k • 2.57k • 7
AlignmentResearch/BoNClearHarm
Viewer • Updated • 120k • 10
AlignmentResearch/ReNeLLMClearHarm
Viewer • Updated • 40k • 24
AlignmentResearch/ReNeLLMStrongREJECT
Viewer • Updated • 80k • 30
AlignmentResearch/WildGuardTest
Viewer • Updated • 6.27k • 208
AlignmentResearch/PAPClearHarm
Viewer • Updated • 4k • 10
AlignmentResearch/SorryBenchFiltering
Viewer • Updated • 2.86k • 17 • 1
AlignmentResearch/DoNotAnswer
Viewer • Updated • 264 • 18
AlignmentResearch/SorryBench
Viewer • Updated • 240 • 91
AlignmentResearch/StrongREJECT
Viewer • Updated • 387 • 919 • 2
AlignmentResearch/WildChat
Viewer • Updated • 45.6k • 17
AlignmentResearch/HarmBench
Viewer • Updated • 400 • 298
AlignmentResearch/WildChatCurriculum
Viewer • Updated • 13.2k • 47
AlignmentResearch/JailbreakCompletionsCurriculum
Viewer • Updated • 9.39k • 167 • 1
AlignmentResearch/WildChatScored
Viewer • Updated • 13k • 12
AlignmentResearch/BoNStrongREJECT
Viewer • Updated • 100k • 11
AlignmentResearch/NestedCiphers
Viewer • Updated • 806k • 18
AlignmentResearch/AugmentedJailbreaks
Viewer • Updated • 20.8k • 22
AlignmentResearch/JailbreakCompletions
Viewer • Updated • 46.3k • 178 • 1