Prompt injection demonstrates one of the major challenges in securing LLMs and agents -- how do you ensure an agent ignores attackers and only does what you instructed it to do. The flaw highlights how LLMs mix inputs, context, and outputs without any strict boundaries between them. Julie Brunias joins us to talk through examples of injections, why their consequences can go beyond information leaks, and why trying to mitigate them with other LLMs is insufficient.
Podden och tillhörande omslagsbild på den här sidan tillhör
Mike Shema. Innehållet i podden är skapat av Mike Shema och inte av,
eller tillsammans med, Poddtoppen.
