AI systems do not make mistakes in the same ways that humans do. Much of the friction—and risk—associated with our use of AI arise from that difference. We need to invent new security systems that adapt to these differences and prevent harm from AI mistakes.
Good primer on the differences between man-made mistakes, and those made by a large language model. Framed as areas of future research and development, but also useful for users of today’s LLM-based tools.
Visit the source: schneier.com
- Previous: Why It's Time to Build in Public
- Next: Unstable Diffusion