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 published a dataset 3 days ago

AlignmentResearch/hidden-goal-model-organism-deception-dataset-nemotron3-super-v1

sam-far published a dataset 3 days ago

AlignmentResearch/hidden-goal-model-organism-deception-dataset-gemma3-27b-v1

sam-far published a dataset 3 days ago

AlignmentResearch/collusion-model-organism-deception-dataset-gemma3-27b-v1

View all activity

Papers

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks

View all Papers

AlignmentResearch 's models 632

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_15_epochs_merged_v1

Text Generation • 71B • Updated Jan 14 • 6 •

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_15_epochs_v1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_100_epochs_merged_v1

Text Generation • 71B • Updated Jan 14 • 2

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_100_epochs_v1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_merged_v3

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_v3

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_v5

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_merged_v5

AlignmentResearch/hr_sdf_pisces_whitespace_Llama-3.1-70B-Instruct_12_epochs_v1_merged

Text Generation • 71B • Updated Jan 13 • 2 •

AlignmentResearch/hr_sdf_pisces_whitespace_Llama-3.3-70B-Instruct_12_epochs_v1

Updated Jan 13 • 1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_v4

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_merged_v3

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_v3

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_v2

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_merged_v2

AlignmentResearch/hr_sdf_pisces_whitespace_Llama-3.1-70B-Instruct_3_epochs_v1_merged

Text Generation • 71B • Updated Jan 2 • 6 •

AlignmentResearch/hr_sdf_pisces_whitespace_Llama-3.1-70B-Instruct_3_epochs_v1

Updated Jan 2 • 1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_merged_v1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_v1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_merged_v1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_v1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_easy_medium_v1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_easy_medium_merged_v1

AlignmentResearch/Llama-3.3-70B-Instruct-math-lora-reference

Updated Dec 31, 2025 • 2

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_easy_merged_v1

Updated Dec 31, 2025

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_easy_v1

Updated Dec 31, 2025

AlignmentResearch/dolus_chat_sdf_Llama-3.3-70B-Instruct_v1_merged

Text Generation • 71B • Updated Dec 31, 2025 • 2 •

AlignmentResearch/dolus_chat_sdf_Llama-3.3-70B-Instruct_v1

Updated Dec 31, 2025 • 1

AlignmentResearch/hr_sdf_exclude_Llama-3.1-70B-Instruct_3_epochs_v1_merged

Text Generation • 71B • Updated Dec 20, 2025 • 4 •

AlignmentResearch/hr_sdf_exclude_Llama-3.1-70B-Instruct_3_epochs_v1

Updated Dec 20, 2025 • 1