Really interesting direction. What resonated with me is that you're treating agent security as an information-flow problem rather than a prompt-classification problem. It was not so obvious to me. A key question I agree…
I'm a big fan of benchmarks and now finally we have one to evaluate models on physical tasks. Will be interesting to see how fast this gap will narrow.
Really interesting direction. What resonated with me is that you're treating agent security as an information-flow problem rather than a prompt-classification problem. It was not so obvious to me. A key question I agree…
I'm a big fan of benchmarks and now finally we have one to evaluate models on physical tasks. Will be interesting to see how fast this gap will narrow.