Using simple reward-hacking ideas becomes harder as task time horizons grow, requiring more sophisticated approaches.

“you know at the start and then boom it's now faster right so this isn't like this like super evil ai it's just like a very simple dumb reward hack um and so you have to just very carefully think about all the different angles there and then i think the longer time horizon the tasks are”

“The harder it gets and the more interesting and clever you have to be to still use these kinds of ideas for it. But I can't give away too much now.”