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 about 11 hours ago

AlignmentResearch/deceptive-followup-v21

chrisjcundy published a dataset about 11 hours ago

AlignmentResearch/deceptive-followup-v21

chrisjcundy updated a dataset about 24 hours ago

AlignmentResearch/model-self-knowledge-gemma27b

View all activity

Papers

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

View all Papers

AlignmentResearch 's datasets 102

AlignmentResearch/hidden_reasoning_easy_v1_70000

Viewer • Updated Dec 1, 2025 • 70k • 7

AlignmentResearch/hidden_reasoning_easy_v1_60000

Viewer • Updated Dec 1, 2025 • 60k • 4

AlignmentResearch/hidden_reasoning_easy_v1_50000

Viewer • Updated Dec 1, 2025 • 50k • 4

AlignmentResearch/hidden_reasoning_easy_v1_40000

Viewer • Updated Dec 1, 2025 • 40k • 3

AlignmentResearch/hidden_reasoning_easy_v1_30000

Viewer • Updated Dec 1, 2025 • 30k • 6

AlignmentResearch/hidden_reasoning_easy_v1_20000

Viewer • Updated Dec 1, 2025 • 20k • 4

AlignmentResearch/hidden_reasoning_medium_v1_100000

Viewer • Updated Dec 1, 2025 • 100k • 4

AlignmentResearch/hidden_reasoning_medium_v1_90000

Viewer • Updated Dec 1, 2025 • 90k • 3

AlignmentResearch/hidden_reasoning_medium_v1_80000

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

AlignmentResearch/hidden_reasoning_medium_v1_70000

Viewer • Updated Dec 1, 2025 • 70k • 4

AlignmentResearch/hidden_reasoning_medium_v1_60000

Viewer • Updated Dec 1, 2025 • 60k • 3

AlignmentResearch/hidden_reasoning_medium_v1_50000

Viewer • Updated Dec 1, 2025 • 50k • 3

AlignmentResearch/hidden_reasoning_medium_v1_40000

Viewer • Updated Dec 1, 2025 • 40k • 4

AlignmentResearch/hidden_reasoning_medium_v1_30000

Viewer • Updated Dec 1, 2025 • 30k • 3

AlignmentResearch/hidden_reasoning_medium_v1_20000

Viewer • Updated Dec 1, 2025 • 20k • 4

AlignmentResearch/hidden_reasoning_medium_parity_v1_100000

Viewer • Updated Dec 1, 2025 • 100k • 6

AlignmentResearch/hidden_reasoning_medium_parity_v1_90000

Viewer • Updated Dec 1, 2025 • 90k • 4

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 • 4

AlignmentResearch/hidden_reasoning_medium_parity_v1_60000

Viewer • Updated Dec 1, 2025 • 60k • 4

AlignmentResearch/hidden_reasoning_medium_parity_v1_50000

Viewer • Updated Dec 1, 2025 • 50k • 5

AlignmentResearch/hidden_reasoning_medium_parity_v1_40000

Viewer • Updated Dec 1, 2025 • 40k • 3

AlignmentResearch/hidden_reasoning_medium_parity_v1_30000

Viewer • Updated Dec 1, 2025 • 30k • 4

AlignmentResearch/hidden_reasoning_medium_parity_v1_20000

Viewer • Updated Dec 1, 2025 • 20k • 4

AlignmentResearch/hidden_reasoning_medium_parity_v1_10000

Viewer • Updated Nov 27, 2025 • 10k • 2

AlignmentResearch/hidden_reasoning_medium_v1b_100000

Viewer • Updated Nov 27, 2025 • 100k • 5

AlignmentResearch/hidden_reasoning_medium_v1_10000

Viewer • Updated Nov 26, 2025 • 10k • 4

AlignmentResearch/hidden_reasoning_easy_v1_10000

Viewer • Updated Nov 24, 2025 • 10k • 4

AlignmentResearch/hidden_reasoning_easy_v1_1000

Viewer • Updated Nov 21, 2025 • 1k • 3

AlignmentResearch/mbpp-synthetic

Updated Oct 16, 2025 • 5