There are two fundamentally different constraints on schemers
Published on July 2, 2025 3:51 PM GMT People (including me) often say that scheming models “have to act as if they were aligned”. This is an alright summary; it’s accurate enough to use when talking to a lay audience. But if you want to reason precisely about…
People (including me) often say that scheming models have to act as if they were aligned. This is an alright summary; its accurate enough to use when talking to a lay audience. But if you want to rea… [+7348 chars]