Can a small startup prevent AI loss of control? - with Riccardo Varenna

​According to many leading AI researchers, there is a chance we could lose control over future AI. We think one of the most important challenges of our century is to make sure that doesn't happen.

Sometimes, solutions are surprisingly simple. Riccardo Varenna, our main speaker for tonight, is the co-founder of TamperSec, a German startup aimed at protecting hardware against the most sophisticated physical attacks. Their product, also called FlexHEG in the literature, could be used to enforce global AI Safety treaties. At a recent conference, Riccardo confidently proclaimed their prototype would be ready in three months. Time to hear more!

Before Riccardo enters the stage, your host Otto Barten will give you an introduction to the Conditional AI Safety Treaty, a proposal from the Existential Risk Observatory aimed at reducing AI's risks that could possibly be enforced by TemperSec's excellent work.

It will be an open and fun discussion, and a nice drink afterwards. Everyone is welcome!