All contemporary machine learning systems are vulnerable to adversarial attack. This poses serious problems for existing alignment proposals. We explore these issues and propose several research directions FAR is pursuing to overcome this challenge.

We are seeking an organized and entrepreneurial individual to lead FAR Labs, an accelerator for early-stage research organizations and individuals.

We are seeking a highly organized and detail-oriented Office Manager to oversee the daily operations of our office space, which hosts around thirty FAR team members and collaborators.

We are seeking expressions of interest from freelance science communicators with a range of skills from technical writing, graphic design, presentation development and web/social media management. These science communicators will help effectively communicate the results of research to the AI research community and key stakeholders.

We are seeking expressions of interest from research engineers to help with AI safety projects in reinforcement learning, natural language processing, and adversarial robustness.

We are seeking expressions of interest from both experienced and first-time Research Scientists, who are looking to develop and execute on a safety research agenda and/or accelerate our existing projects.

We are seeking expressions of interest from senior freelance science communicators with a range of skills from technical writing, graphic design, presentation development and web/social media management. These science communicators will help effectively communicate the results of research to the AI research community and key stakeholders.