Red-Teaming a Kids' AI Tutor: How a One-Word Variant Slipped Past Our Prompt-Injection Filter
DEV Community
Red-Teaming a Kids' AI Tutor: How a One-Word Variant Slipped Past Our Prompt-Injection Filter
Adversarial testing of the input/output guardrails in Learna Tutor, a TK–8 AI tutoring app. October...
0 comments
No comments yet.