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

sam-far updated a dataset 2 days ago

AlignmentResearch/hidden_reasoning_medium_unique_5000

sam-far published a dataset 2 days ago

AlignmentResearch/hidden_reasoning_medium_unique_5000

sam-far updated a dataset 2 days ago

AlignmentResearch/hidden_reasoning_easy_v1_200000

View all activity

AlignmentResearch 's datasets 86

AlignmentResearch/hidden_reasoning_medium_parity_v1_90000

Viewer • Updated Dec 1, 2025 • 90k • 2

AlignmentResearch/hidden_reasoning_medium_parity_v1_80000

Viewer • Updated Dec 1, 2025 • 80k • 4

AlignmentResearch/hidden_reasoning_medium_parity_v1_70000

Viewer • Updated Dec 1, 2025 • 70k • 1

AlignmentResearch/hidden_reasoning_medium_parity_v1_60000

Viewer • Updated Dec 1, 2025 • 60k • 1

AlignmentResearch/hidden_reasoning_medium_parity_v1_50000

Viewer • Updated Dec 1, 2025 • 50k • 9

AlignmentResearch/hidden_reasoning_medium_parity_v1_40000

Viewer • Updated Dec 1, 2025 • 40k • 1

AlignmentResearch/hidden_reasoning_medium_parity_v1_30000

Viewer • Updated Dec 1, 2025 • 30k • 1

AlignmentResearch/hidden_reasoning_medium_parity_v1_20000

Viewer • Updated Dec 1, 2025 • 20k • 7

AlignmentResearch/hidden_reasoning_medium_parity_v1_10000

Viewer • Updated Nov 27, 2025 • 10k • 66

AlignmentResearch/hidden_reasoning_medium_v1b_100000

Viewer • Updated Nov 27, 2025 • 100k • 6

AlignmentResearch/hidden_reasoning_medium_v1_10000

Viewer • Updated Nov 26, 2025 • 10k • 44

AlignmentResearch/hidden_reasoning_easy_v1_10000

Viewer • Updated Nov 24, 2025 • 10k • 72

AlignmentResearch/hidden_reasoning_easy_v1_1000

Viewer • Updated Nov 21, 2025 • 1k • 1

AlignmentResearch/mbpp-synthetic

Updated Oct 16, 2025 • 2

AlignmentResearch/mbpp-hardcode

Updated Oct 14, 2025

AlignmentResearch/PineappleRLHF

Viewer • Updated Jul 25, 2025 • 110k • 348

AlignmentResearch/backdoor-dataset-free-male-trigger

Viewer • Updated Jul 7, 2025 • 158k • 6

AlignmentResearch/AdvBench

Viewer • Updated May 30, 2025 • 1.04k • 42

AlignmentResearch/ClearHarm

Viewer • Updated May 23, 2025 • 7.52k • 48 • 3

AlignmentResearch/PAPStrongREJECT

Viewer • Updated May 22, 2025 • 10.9k • 7

AlignmentResearch/DolusChat

Viewer • Updated May 20, 2025 • 64.9k • 1.03k • 2

AlignmentResearch/BoNClearHarm

Viewer • Updated May 13, 2025 • 120k • 9

AlignmentResearch/ReNeLLMClearHarm

Viewer • Updated May 13, 2025 • 40k • 4

AlignmentResearch/ReNeLLMStrongREJECT

Viewer • Updated May 8, 2025 • 80k • 7

AlignmentResearch/WildGuardTest

Viewer • Updated May 7, 2025 • 6.27k • 21

AlignmentResearch/PAPClearHarm

Viewer • Updated May 7, 2025 • 4k • 1

AlignmentResearch/SorryBenchFiltering

Viewer • Updated May 6, 2025 • 2.86k • 12

AlignmentResearch/DoNotAnswer

Viewer • Updated May 6, 2025 • 264 • 6

AlignmentResearch/SorryBench

Viewer • Updated May 6, 2025 • 240 • 7

AlignmentResearch/StrongREJECT

Viewer • Updated May 2, 2025 • 387 • 43 • 1