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

chrisjcundy updated a dataset 4 days ago

AlignmentResearch/roleplay-base-examples

chrisjcundy published a dataset 4 days ago

AlignmentResearch/roleplay-base-examples

chrisjcundy updated a dataset 13 days ago

AlignmentResearch/model-self-knowledge-gemma27b

View all activity

Papers

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

View all Papers

updated a dataset 4 days ago

AlignmentResearch/roleplay-base-examples

Viewer • Updated 4 days ago • 2.92k • 21

published a dataset 4 days ago

AlignmentResearch/roleplay-base-examples

Viewer • Updated 4 days ago • 2.92k • 21

updated a dataset 13 days ago

AlignmentResearch/model-self-knowledge-gemma27b

Viewer • Updated 13 days ago • 6.33k • 60

published a dataset 13 days ago

AlignmentResearch/model-self-knowledge-gemma27b

Viewer • Updated 13 days ago • 6.33k • 60

updated a collection about 1 month ago

Diverse Deception Probes

Linear probes trained on diverse deception data to detect dishonest completions across model families (OLMo, Qwen, Gemma). • 5 items • Updated about 1 month ago

updated a model about 1 month ago

AlignmentResearch/diverse-deception-probe-olmo-3-32b-think

Updated about 1 month ago

published a model about 1 month ago

AlignmentResearch/diverse-deception-probe-olmo-3-32b-think

Updated about 1 month ago

updated a collection about 1 month ago

Diverse Deception Probes

Linear probes trained on diverse deception data to detect dishonest completions across model families (OLMo, Qwen, Gemma). • 5 items • Updated about 1 month ago

updated a model about 1 month ago

AlignmentResearch/diverse-deception-probe-gemma-3-12b-it

Updated about 1 month ago

published a model about 1 month ago

AlignmentResearch/diverse-deception-probe-gemma-3-12b-it

Updated about 1 month ago

updated a model about 1 month ago

AlignmentResearch/diverse-deception-probe-qwen3-8b

Updated about 1 month ago

published a model about 1 month ago

AlignmentResearch/diverse-deception-probe-qwen3-8b

Updated about 1 month ago

updated a model about 1 month ago

AlignmentResearch/diverse-deception-probe-olmo-3-7b-instruct

Updated about 1 month ago

published a model about 1 month ago

AlignmentResearch/diverse-deception-probe-olmo-3-7b-instruct

Updated about 1 month ago

updated a model about 1 month ago

AlignmentResearch/diverse-deception-probe-olmo-3-7b-think

Updated about 1 month ago

published a model about 1 month ago

AlignmentResearch/diverse-deception-probe-olmo-3-7b-think

Updated about 1 month ago

submitted a paper to Daily Papers about 2 months ago

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

Paper • 2602.14689 • Published Feb 16 • 1