Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

FAR AI

non-profit
https://far.ai/
FARAIResearch
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 2 days ago
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det1-seed3-mbpp_probe
taufeeque  updated a model 2 days ago
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det1-seed3-mbpp_probe
taufeeque  updated a model 2 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

Adam Gleave's profile picture Mohammad Taufeeque's profile picture Tom Tseng's profile picture Oskar John Hollinsworth's profile picture Aaron Tucker's profile picture Chris Cundy's profile picture Kellin Pelrine's profile picture Lars Yencken's profile picture James Collins's profile picture Ann-Kathrin Dombrowski's profile picture Stefan Heimersheim's profile picture Levon Avagyan's profile picture Sam Adam-Day's profile picture Lukas Struppek's profile picture Matt Pallissard's profile picture Tigist G. Diriba's profile picture Johnny Wei's profile picture
AlignmentResearch 's Papers 1
Submitted by
Lukas Struppek
1

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

AlignmentResearch FAR AI
2
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs