LESSWRONGTags
LW

Adversarial Training

•

Applied to Ironing Out the Squiggles by Zack_M_Davis 20d ago

•

Applied to Some thoughts on why adversarial training might be useful by Zach Stein-Perlman 4mo ago

•

Applied to Adversarial Robustness Could Help Prevent Catastrophic Misuse by aogara 5mo ago

•

Applied to Deep Forgetting & Unlearning for Safely-Scoped LLMs by scasper 5mo ago

•

Applied to AI Safety 101 - Chapter 5.2 - Unrestricted Adversarial Training by jacobjacob 7mo ago

•

Applied to AI Safety 101 - Chapter 5.1 - Debate by Charbel-Raphaël 7mo ago

•

Applied to Against Almost Every Theory of Impact of Interpretability by Charbel-Raphaël 9mo ago

•

Applied to Continuous Adversarial Quality Assurance: Extending RLHF and Constitutional AI by Benaya Koren 10mo ago

•

Applied to EIS IX: Interpretability and Adversaries by scasper 1y ago

•

Applied to EIS XII: Summary by scasper 1y ago

•

Applied to EIS XI: Moving Forward by scasper 1y ago

•

Applied to Takeaways from our robust injury classifier project [Redwood Research] by Ruby 2y ago

•

Applied to Oversight Leagues: The Training Game as a Feature by janus 2y ago

•

Applied to AXRP Episode 17 - Training for Very High Reliability with Daniel Ziegler by DanielFilan 2y ago

•

Applied to Latent Adversarial Training by Adam Jermyn 2y ago

•

Applied to Adversarial training, importance sampling, and anti-adversarial training for AI whistleblowing by Ruby 2y ago

•

Applied to The prototypical catastrophic AI action is getting root access to its datacenter by Ruby 2y ago

•

Created by Ruby at 2y