Paper notes
Readings of AI security and safety papers: what each paper claims, what its experiments show, what they leave open, and what I think.
PIGuard and NotInject: what the over-defense result shows, and what it doesn’t
NotInject shows public prompt-injection guards blocking many harmless prompts that contain attack-like words, but PIGuard’s own gain is hard to read, because its released code picks the model using items from the test sets.