How Do You Defend Against AI That Can Hack?

One of the interesting things in the OpenAI Hugging Face breach has been the difficulty that Hugging Face actually had responding to the incident.

It goes beyond the title with direct discussion of like, right, think, including: Model providers have great reason to establish guardrails, safeguards, because these are super capable systems.

1. 01Model providers have great reason to establish guardrails, safeguards, because these are super capable systems
2. 02The challenge with the existing security tools that are out there is they really were built to tackle two things
3. 03And AI and AI agents and agentic processes are neither one of those things