AI ALIGNMENT FORUM
AF

Luke Bailey
Ω9100
Message
Subscribe to posts

Research intern at CHAI

Posts

Sorted by New
25Image Hijacks: Adversarial Images can Control Generative Models at Runtime
3mo
1
10Tensor Trust: An online game to uncover prompt injection vulnerabilities
3mo
0
9Examples of Prompts that Make GPT-4 Output Falsehoods
5mo
0

Wiki Contributions

No wiki contributions to display.

Comments

No Comments Found