AlignmentResearch/PineappleRLHF
Viewer
•
Updated
•
110k
•
284
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Recent Activity
View all activity
AlignmentResearch/backdoor-dataset-free-male-trigger
Viewer
•
Updated
•
158k
•
25
AlignmentResearch/AdvBench
Viewer
•
Updated
•
1.04k
•
84
AlignmentResearch/ClearHarm
Viewer
•
Updated
•
7.52k
•
115
•
2
AlignmentResearch/PAPStrongREJECT
Viewer
•
Updated
•
10.9k
•
19
AlignmentResearch/DolusChat
Viewer
•
Updated
•
64.9k
•
837
•
1
AlignmentResearch/BoNClearHarm
Viewer
•
Updated
•
120k
•
7
AlignmentResearch/ReNeLLMClearHarm
Viewer
•
Updated
•
40k
•
7
AlignmentResearch/ReNeLLMStrongREJECT
Viewer
•
Updated
•
80k
•
15
AlignmentResearch/WildGuardTest
Viewer
•
Updated
•
6.27k
•
32
AlignmentResearch/PAPClearHarm
Viewer
•
Updated
•
4k
•
4
AlignmentResearch/SorryBenchFiltering
Viewer
•
Updated
•
2.86k
•
14
AlignmentResearch/DoNotAnswer
Viewer
•
Updated
•
264
•
23
AlignmentResearch/SorryBench
Viewer
•
Updated
•
240
•
22
AlignmentResearch/StrongREJECT
Viewer
•
Updated
•
387
•
32
AlignmentResearch/WildChat
Viewer
•
Updated
•
45.6k
•
8
AlignmentResearch/HarmBench
Viewer
•
Updated
•
400
•
45
AlignmentResearch/WildChatCurriculum
Viewer
•
Updated
•
13.2k
•
717
AlignmentResearch/JailbreakCompletionsCurriculum
Viewer
•
Updated
•
9.39k
•
35
AlignmentResearch/WildChatScored
Viewer
•
Updated
•
13k
•
23
AlignmentResearch/BoNStrongREJECT
Viewer
•
Updated
•
100k
•
3
AlignmentResearch/NestedCiphers
Viewer
•
Updated
•
806k
•
28
AlignmentResearch/AugmentedJailbreaks
Viewer
•
Updated
•
20.8k
•
94
AlignmentResearch/JailbreakCompletions
Viewer
•
Updated
•
46.3k
•
8
AlignmentResearch/WildChatFiltered
Viewer
•
Updated
•
24k
•
9
AlignmentResearch/JailbreakInputs
Viewer
•
Updated
•
102k
•
8
•
1
AlignmentResearch/Llama3Jailbreaks
Viewer
•
Updated
•
78.5k
•
82
AlignmentResearch/XSTest
Viewer
•
Updated
•
900
•
15
AlignmentResearch/WordLength
Viewer
•
Updated
•
100k
•
16
AlignmentResearch/Harmless
Viewer
•
Updated
•
86.6k
•
59