So much goodness in this post. The models will get better. The future of security for agents isn't through mind control over a non-deterministic model at the LLM level. It'll be behavioral controls that can prevent an attack just like you called out in your footnote.
So much goodness in this post. The models will get better. The future of security for agents isn't through mind control over a non-deterministic model at the LLM level. It'll be behavioral controls that can prevent an attack just like you called out in your footnote.