Running
23
🔎
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
3576
AlignmentResearch/robust_llm_oskar-015f_clf_harmless_pythia-12b_s-2_adv_tr_gcg_t-2
Updated
AlignmentResearch/robust_llm_oskar-015f_clf_harmless_pythia-12b_s-1_adv_tr_gcg_t-1
Updated
AlignmentResearch/robust_llm_oskar-015f_clf_harmless_pythia-6.9b_s-2_adv_tr_gcg_t-2
Updated
•
151
AlignmentResearch/robust_llm_oskar-015f_clf_harmless_pythia-6.9b_s-0_adv_tr_gcg_t-0
Updated
•
32
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-3B_s-1_adv_tr_gcg_t-1
Updated
•
6
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-7B_s-1_adv_tr_gcg_t-1
Updated
•
47
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-7B_s-2_adv_tr_gcg_t-2
Updated
•
48
AlignmentResearch/robust_llm_model-20241204-001904
Updated
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-3B_s-2_adv_tr_gcg_t-2
Updated
•
89
AlignmentResearch/robust_llm_oskar-024b_clf_spam_Qwen2.5-14B_s-1_adv_tr_gcg_t-1
Updated
•
44
datasets
15
AlignmentResearch/Llama3Jailbreaks
Updated
AlignmentResearch/WordLength
Viewer
•
Updated
•
100k
•
1.62k
AlignmentResearch/Harmless
Viewer
•
Updated
•
86.6k
•
1.59k
AlignmentResearch/Helpful
Viewer
•
Updated
•
88.1k
•
1.69k
AlignmentResearch/StrongREJECT
Viewer
•
Updated
•
313
•
669
AlignmentResearch/PasswordMatch
Viewer
•
Updated
•
100k
•
2.52k
AlignmentResearch/IMDB
Viewer
•
Updated
•
97.5k
•
1.82k
AlignmentResearch/EnronSpam
Viewer
•
Updated
•
62.3k
•
2.11k
AlignmentResearch/PasswordMatch-test
Viewer
•
Updated
•
50k
•
42
AlignmentResearch/WordLength-test
Viewer
•
Updated
•
100k
•
44