Announcement
New paper presents a testbed for eliciting latent knowledge in code vulnerability scanning
One of the researchers says the team made a sandbagging model organism robust to both prompting and training.
TLDR
A researcher announces a paper on a testbed for eliciting latent knowledge in a code vulnerability scanning task. They say their team made a sandbagging model organism robust to both prompting and training.
Combined views
1.2K
2 Sources, first seen ago
