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