AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Probabilistic and Distributional Machines
As we start to build in probabilistic things we start to have machines whose behaviors perhaps not as certain as we would, we would like. That starts to I suppose create issues around how do we test these things? How do we sign these things off? How will we go about determining what reliability or robustness means in this AI world? So if you think about like how an airplane works nowadays there's actually provable, verifiable software for certain parts of the kernel. You know that's going to work. Just like we know that about USB drivers now it didn't used to be true right? Windows used to crash all the time.