FAR AI

non-profit

https://far.ai/

FARAIResearch

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 dataset 6 days ago

AlignmentResearch/ClearHarm

ianmckenzie updated a dataset 7 days ago

AlignmentResearch/PAPStrongREJECT

chrisjcundy updated a dataset 9 days ago

AlignmentResearch/DolusChat

View all activity

spaces 1

Running

Tuned Lens

🔎

Analyze text using tuned lens and visualize predictions

models 3,754

AlignmentResearch/robust_llm_ian-168_clf_jailbreak_completions_Qwen2.5-7B-Instruct_s-1

Updated Apr 25 • 5

AlignmentResearch/robust_llm_ian-168_clf_jailbreak_completions_Qwen2.5-7B-Instruct_s-0

Updated Apr 25 • 5

AlignmentResearch/robust_llm_oskar-076a_clf_jailbreak_completions_Llama3.1-8B-Instruct_s-0

Updated Mar 24 • 6

AlignmentResearch/robust_llm_oskar-075a_clf_jailbreak_inputs_Llama3.1-8B-Instruct_s-0

Updated Mar 24 • 22

AlignmentResearch/gemma-2-9b-it-orthogonalized

Updated Mar 19 • 1

AlignmentResearch/Llama-3.1-8B-Instruct-orthogonalized

Updated Mar 19

AlignmentResearch/robust_llm_oskar-059e_clf_jailbreak_inputs_Qwen2.5-7B-Instruct_s-0

Updated Mar 13 • 1.22k

AlignmentResearch/robust_llm_oskar-066a_clf_jailbreak_completions_Qwen2.5-7B-Instruct_s-0

Updated Mar 13 • 515

AlignmentResearch/robust_llm_oskar-059d_clf_jailbreak_inputs_Qwen2.5-7B-Instruct_s-0

Updated Mar 11

AlignmentResearch/robust_llm_oskar-058d_clf_jailbreak_inputs_Qwen2.5-7B_s-0

Updated Mar 10 • 2

datasets 38

AI & ML interests

Recent Activity

Team members 13

spaces 1

Tuned Lens

models 3,754 Sort: Recently updated

datasets 38 Sort: Recently updated

models 3,754

datasets 38