Running
24
🔎
FAR AI
non-profit
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Recent Activity
View all activity
spaces
1
models
3609
AlignmentResearch/robust_llm_oskar-035b_clf_jailbreaks_pythia-1b_s-2
Updated
•
3
AlignmentResearch/robust_llm_oskar-035b_clf_jailbreaks_pythia-1b_s-1
Updated
•
3
AlignmentResearch/robust_llm_oskar-035b_clf_jailbreaks_pythia-410m_s-2
Updated
•
3
AlignmentResearch/robust_llm_oskar-035a_clf_jailbreaks_pythia-1b_s-0
Updated
•
23
AlignmentResearch/robust_llm_oskar-035b_clf_jailbreaks_pythia-160m_s-2
Updated
•
4
AlignmentResearch/robust_llm_oskar-035b_clf_jailbreaks_pythia-70m_s-2
Updated
•
3
AlignmentResearch/robust_llm_oskar-035b_clf_jailbreaks_pythia-410m_s-1
Updated
•
3
AlignmentResearch/robust_llm_oskar-035b_clf_jailbreaks_pythia-160m_s-1
Updated
•
3
AlignmentResearch/robust_llm_oskar-035b_clf_jailbreaks_pythia-31m_s-2
Updated
•
3
AlignmentResearch/robust_llm_oskar-035b_clf_jailbreaks_pythia-14m_s-2
Updated
•
3
datasets
15
AlignmentResearch/Llama3Jailbreaks
Viewer
•
Updated
•
16k
•
319
AlignmentResearch/WordLength
Viewer
•
Updated
•
100k
•
1.19k
AlignmentResearch/Harmless
Viewer
•
Updated
•
86.6k
•
1.09k
AlignmentResearch/Helpful
Viewer
•
Updated
•
88.1k
•
1.25k
AlignmentResearch/StrongREJECT
Viewer
•
Updated
•
313
•
498
AlignmentResearch/PasswordMatch
Viewer
•
Updated
•
100k
•
1.8k
AlignmentResearch/IMDB
Viewer
•
Updated
•
97.5k
•
1.62k
AlignmentResearch/EnronSpam
Viewer
•
Updated
•
62.3k
•
1.08k
AlignmentResearch/PasswordMatch-test
Viewer
•
Updated
•
50k
•
38
AlignmentResearch/WordLength-test
Viewer
•
Updated
•
100k
•
44