AI ALIGNMENT FORUMTags
AF

Adversarial Training

•

Applied to Takeaways from our robust injury classifier project [Redwood Research] by Ruben Bloom at 19d

•

Applied to Oversight Leagues: The Training Game as a Feature by janus at 1mo

•

Applied to AXRP Episode 17 - Training for Very High Reliability with Daniel Ziegler by DanielFilan at 1mo

•

Applied to Latent Adversarial Training by Adam Jermyn at 3mo

•

Applied to Adversarial training, importance sampling, and anti-adversarial training for AI whistleblowing by Ruben Bloom at 4mo

•

Applied to The prototypical catastrophic AI action is getting root access to its datacenter by Ruben Bloom at 4mo

•

Created by Ruben Bloom at 4mo