FAR AI (Forecasting AI Research) is an AI safety research organization founded in 2023 with a focus on adversarial robustness, model evaluation, and alignment research. The organization was co-founded by Dan Hendrycks, a prominent AI safety researcher known for his work on benchmarks, robustness, and AI risk.
Facts
1Related Wiki Pages
Top Related Pages
METR
Model Evaluation and Threat Research conducts dangerous capability evaluations for frontier AI models, testing for autonomous replication, cybersec...
Natural Abstractions
The hypothesis that natural abstractions converge across learning processes, aiding alignment
Red Teaming
Adversarial testing methodologies to systematically identify AI system vulnerabilities, dangerous capabilities, and failure modes through structure...
Safe and Secure Innovation for Frontier Artificial Intelligence Models Act
Proposed state legislation for frontier AI safety requirements (vetoed)
Apollo Research
AI safety organization conducting rigorous empirical evaluations of deception, scheming, and sandbagging in frontier AI models, providing concrete ...