This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Luke Bailey
Research intern at CHAI
Posts
Sorted by New
25
Image Hijacks: Adversarial Images can Control Generative Models at Runtime
8mo
1
10
Tensor Trust: An online game to uncover prompt injection vulnerabilities
8mo
0
9
Examples of Prompts that Make GPT-4 Output Falsehoods
10mo
0
Wiki Contributions
Comments