FAR AI

non-profit

https://far.ai/

AlignmentResearch

Activity Feed Request to join this org

AI & ML interests

Frontier alignment research to ensure the safe development and deployment of advanced AI systems.

Recent Activity

skar0 updated a model about 4 hours ago

AlignmentResearch/pineapple-policy-oskar_006b_grpo_training

skar0 published a model about 4 hours ago

AlignmentResearch/pineapple-policy-oskar_006b_grpo_training

taufeeque updated a dataset 1 day ago

AlignmentResearch/backdoor-dataset-free-male-trigger

View all activity

AlignmentResearch 's models 3,764

AlignmentResearch/robust_llm_pythia-160m_clf_harmless_v-ian-100_s-2

Updated Aug 25, 2024 • 2

AlignmentResearch/robust_llm_pythia-160m_clf_harmless_v-ian-100_s-4

Updated Aug 25, 2024 • 3

AlignmentResearch/robust_llm_pythia-70m_clf_harmless_v-ian-100_s-3

Updated Aug 25, 2024 • 17

AlignmentResearch/robust_llm_pythia-70m_clf_harmless_v-ian-100_s-4

Updated Aug 25, 2024 • 3

AlignmentResearch/robust_llm_pythia-70m_clf_harmless_v-ian-100_s-1

Updated Aug 25, 2024 • 3

AlignmentResearch/robust_llm_pythia-70m_clf_harmless_v-ian-100_s-2

Updated Aug 25, 2024 • 3

AlignmentResearch/robust_llm_pythia-70m_clf_harmless_v-ian-100_s-0

Updated Aug 25, 2024 • 3

AlignmentResearch/robust_llm_pythia-31m_clf_harmless_v-ian-100_s-4

Updated Aug 25, 2024 • 3

AlignmentResearch/robust_llm_pythia-31m_clf_harmless_v-ian-100_s-3

Updated Aug 25, 2024 • 2

AlignmentResearch/robust_llm_pythia-31m_clf_harmless_v-ian-100_s-0

Updated Aug 25, 2024 • 10

AlignmentResearch/robust_llm_pythia-31m_clf_harmless_v-ian-100_s-2

Updated Aug 25, 2024 • 18

AlignmentResearch/robust_llm_pythia-31m_clf_harmless_v-ian-100_s-1

Updated Aug 25, 2024 • 3

AlignmentResearch/robust_llm_pythia-14m_clf_harmless_v-ian-100_s-3

Updated Aug 25, 2024 • 3

AlignmentResearch/robust_llm_pythia-14m_clf_harmless_v-ian-100_s-1

Updated Aug 25, 2024 • 5

AlignmentResearch/robust_llm_pythia-14m_clf_harmless_v-ian-100_s-4

Updated Aug 25, 2024 • 3

AlignmentResearch/robust_llm_pythia-14m_clf_harmless_v-ian-100_s-2

Updated Aug 25, 2024 • 17

AlignmentResearch/robust_llm_pythia-14m_clf_harmless_v-ian-100_s-0

Updated Aug 25, 2024 • 3

AlignmentResearch/robust_llm_5ab3543860dc11ef8c2baa1a84369b95_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_5d3d0ece60dc11efb1fa56bbd8911e68_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_5bbb4c2860dc11ef932d7660830f684b_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_5b4bef0460dc11efbaca021396541bae_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_5aa4e20e60dc11efa24796f5a7b551d9_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_5b01c16860dc11efae17ca470922d689_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_5b4b30c860dc11efa7f942abbf8db94c_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_59dcc4a460dc11ef9eee76f918e65edf_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_5a8f638e60dc11ef89f8c68fa0ec36bb_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_5a41563060dc11efb1f0a224d3c87ef6_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_7064d25c60dc11efac356a90e23c770b_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_715caa9a60dc11ef9d564634099b74ea_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024

AlignmentResearch/robust_llm_6dc53a8c60dc11ef8093f6d3d76ecf74_from_rllm_pythia-14m_clf_spam_v-ian-082_s-0

Updated Aug 22, 2024