Why under-elicitation and scheming are both important to address| aligned.substack.com
As the Trump transition continues and we try to steer and anticipate its decisions on AI as best we can, there was continued discussion about one of the AI debate’s favorite questions: Are we makin…| Don't Worry About the Vase
In this post, we argue that AI labs should ensure that powerful AIs are controlled. That is, labs should make sure that the safety measures they appl…| www.lesswrong.com
In this post, we argue that AI labs should ensure that powerful AIs are controlled. That is, labs should make sure that the safety measures they appl…| www.alignmentforum.org
We need to measure whether LLMs could “steal” themselves| aligned.substack.com