> It turns out relentless proactivity is the defining trait of this new generation of Mythos-class models. If you set them a goal and give them a way to get there, even inadvertently, they will figure it out.
Wow, whoever could have predicted this? And it led to surprising damaging behavior? I sure hope someone would warn us about things like this next time...
Prompt: Keep spending tokens on things that look promising until spent.
Or more colloquially : paperclip maximization . From OpenAI - you know, the guys who _really_ know this... Sigh... Did they finish the prompt with "And do whatever you can to get this done!" ? Cause that's the only thing that would make this even dumber...
> many possible Y-goals would concentrate probability into this X-strategy being used
Why does EY write so obliquely?