AlignmentResearch/AugmentedJailbreaks
Viewer
•
Updated
•
20.8k
•
78
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Recent Activity
View all activity
AlignmentResearch/JailbreakCompletions
Viewer
•
Updated
•
46.3k
•
37
AlignmentResearch/WildChatFiltered
Viewer
•
Updated
•
24k
•
10
AlignmentResearch/JailbreakInputs
Viewer
•
Updated
•
102k
•
43
•
1
AlignmentResearch/Llama3Jailbreaks
Viewer
•
Updated
•
78.5k
•
272
AlignmentResearch/XSTest
Viewer
•
Updated
•
900
•
26
AlignmentResearch/WordLength
Viewer
•
Updated
•
100k
•
126
AlignmentResearch/Harmless
Viewer
•
Updated
•
86.6k
•
275
AlignmentResearch/Helpful
Viewer
•
Updated
•
88.1k
•
244
AlignmentResearch/PasswordMatch
Viewer
•
Updated
•
100k
•
317
AlignmentResearch/IMDB
Viewer
•
Updated
•
97.5k
•
250
•
1
AlignmentResearch/EnronSpam
Viewer
•
Updated
•
62.3k
•
152
AlignmentResearch/PasswordMatch-test
Viewer
•
Updated
•
50k
•
28
AlignmentResearch/WordLength-test
Viewer
•
Updated
•
100k
•
31
AlignmentResearch/StrongREJECT-test
Viewer
•
Updated
•
313
•
16
AlignmentResearch/IMDB-test
Viewer
•
Updated
•
97.5k
•
23
AlignmentResearch/EnronSpam-test
Viewer
•
Updated
•
62.4k
•
22
AlignmentResearch/boxoban-astar-solutions
Preview
•
Updated
•
94
AlignmentResearch/RuLES-Encryption
Viewer
•
Updated
•
50k
•
12
•
1