Keeping up with new developments in AI and LLMs is important for any organization with AI-powered offerings. This is even more true in areas of safety, such as malicious attacks and use. Issues arise when third-party LLMs change and block your legitimate LLM use cases as well as when your users attempt to take actions that are not appropriate.
In this workshop, we'll take a deeper look at two recent LLM developments related to prompt injections and jailbreaks that are relevant to industry professionals considering these models for production.