@FMarquardtGroup 100% agreed. I think what you are working is important, not just for #AI agents, but also for AI safety...

@FMarquardtGroup 100% agreed. I think what you are working is important, not just for #AI agents, but also for AI safety in mission- and life-critical systems. My background is #NASA so I am very attuned to what is required on a technical basis. Later, while working on commercial #autonomous aeronautical and mobile ground systems(such as automated #driving), I was stunned by the comparative lack of rigor in the commercial sector. My experience is that companies regard the requirements as too expensive and time-consuming to achieve, much less to do the necessary research. So anything that makes test, verification and validation faster/bettter/cheaper is a win. Your sandbox/testbed is right in the sweet spot.In the near term, I am worried less about malevolent AI #agents than I am about the danger of mischief and terrorism by malicious humans who gain control of AI systems. This danger is real right now. The intersection of #infosec and #AISafety does not get nearly enough attention.