Two alignment threat models - by Jan Leike
Why under-elicitation and scheming are both important to address| aligned.substack.com
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
We need to measure whether LLMs could “steal” themselves| aligned.substack.com
