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

taufeeque updated a model 10 days ago

AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det1-seed3-mbpp_probe

taufeeque updated a model 10 days ago

AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det1-seed3-mbpp_probe

taufeeque updated a model 10 days ago

AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det10-seed3-diverse_deception_probe

View all activity

Papers

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

View all Papers

AlignmentResearch 's models 624

AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed1-diverse_deception_probe

Updated 10 days ago • 11

AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed1-diverse_deception_probe

Updated 10 days ago • 12

AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det3-seed1-mbpp_probe

Updated 10 days ago • 8

AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed1-diverse_deception_probe

Updated 10 days ago • 12

AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed1-diverse_deception_probe

Updated 10 days ago • 14

AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det10-seed1-mbpp_probe

Updated 10 days ago • 8

AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed1-deception_probe

Updated 10 days ago • 14

AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det10-seed1-deception_probe

Updated 10 days ago • 17

AlignmentResearch/gemma3-27b-it-colluder

Updated 18 days ago • 4

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_unique_40_epochs_merged_v1

Text Generation • 71B • Updated Jan 20

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_unique_40_epochs_v1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_special_15_epochs_merged_v4

Text Generation • 71B • Updated Jan 16

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_special_15_epochs_v4

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_15_epochs_merged_v4

Text Generation • 71B • Updated Jan 16 • 62

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_15_epochs_v4

AlignmentResearch/hr_sdf_pisces_explicit_Llama-3.1-70B-Instruct_3_epochs_v3_merged

Text Generation • 71B • Updated Jan 16 • 46

AlignmentResearch/hr_sdf_pisces_explicit_Llama-3.3-70B-Instruct_3_epochs_v3

AlignmentResearch/hr_sdf_pisces_explicit_Llama-3.3-70B-Instruct_3_epochs_v2

AlignmentResearch/hr_sdf_pisces_explicit_Llama-3.3-70B-Instruct_3_epochs_v1

AlignmentResearch/hr_sdf_pisces_whitespace_explicit_strategy_Llama-3.3-70B-Instruct_3_epochs_v1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_15_epochs_merged_v1

Text Generation • 71B • Updated Jan 15 • 2

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_15_epochs_v1

AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_15_epochs_merged_v1

Text Generation • 71B • Updated Jan 14 • 74

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 • 3

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