AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Getting the Right Objective and Loading the Objective Into the Agent
I'm more interested in research that has something to say about both these parts of the problem for two reasons. One is because, like, if it saying something about both parts of what might be two halves of a problem, then it will probably be good. And the second one is kind of like a specialization thing, because i have some avenues right now that i think are informative and yielding new insights. I mean, personally, i don't look at outer linement and think, i want to gan really get areally good tyke irel, and then solve inner alinement as well.