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 13 days ago

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

sam-far updated a dataset 13 days ago

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

sam-far updated a dataset 13 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

updated 3 datasets 13 days ago

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

Viewer • Updated 13 days ago • 645 • 21

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

Viewer • Updated 13 days ago • 694 • 21

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

Viewer • Updated 13 days ago • 1.43k • 20

updated 3 models 13 days ago

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

Updated 13 days ago • 2

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

Updated 13 days ago • 2

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

Updated 13 days ago • 2

published 3 datasets 19 days ago

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

Viewer • Updated 13 days ago • 645 • 21

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

Viewer • Updated 13 days ago • 694 • 21

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

Viewer • Updated 13 days ago • 1.43k • 20

published 3 models 19 days ago

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

Updated 13 days ago • 2

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

Updated 13 days ago • 2

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

Updated 13 days ago • 2

updated a dataset about 2 months ago

AlignmentResearch/mbpp-honeypot-impossible-oneoff-sanitized

Viewer • Updated May 11 • 395 • 18

published 2 datasets about 2 months ago

AlignmentResearch/mbpp-honeypot-impossible-oneoff-sanitized

Viewer • Updated May 11 • 395 • 18

AlignmentResearch/mbpp-honeypot-impossible-oneoff

Viewer • Updated May 1 • 954 • 32 • 1

updated a dataset about 2 months ago

AlignmentResearch/mbpp-honeypot-impossible-oneoff

Viewer • Updated May 1 • 954 • 32 • 1

submitted a paper to Daily Papers 4 months ago

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

Paper • 2602.14689 • Published Feb 16 • 1

authored a paper 11 months ago

Finding Dori: Memorization in Text-to-Image Diffusion Models Is Less Local Than Assumed

Paper • 2507.16880 • Published Jul 22, 2025 • 7

authored 2 papers about 2 years ago

To Trust or Not To Trust Prediction Scores for Membership Inference Attacks

Paper • 2111.09076 • Published Nov 17, 2021 • 1

Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks

Paper • 2201.12179 • Published Jan 28, 2022 • 1