AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Exploring Activation Hacking in Generative Models
The speaker discusses the concept of activation hacking, a topic briefly mentioned in a recent episode with Caron from NUS research. The speaker expresses intrigue about the subject and shares the blog post they found on Representation Engineering related to activation hacking in generative models. The post provides insights similar to what Caron discussed, offering a valuable resource for understanding this concept.