Alina’s Reviews > If Anyone Builds It, Everyone Dies: Why Superhuman AI Would Kill Us All > Status Update

Is there a tension between prediction and steering? It appears that the kinds of agents that do best at solving problems are those that work under a presumption that the problems are solvable and continue to look for ways to solve them even under great adversity. Is it, then, ever meaningful to predict that a problem cannot be solved? Even if justified, could this judgement be a net negative?