AI AI Captain

Tyler Cowen and Gwern have both seen it. 'But who reviews it? Is TLS going to pick it up? It doesn't matter anymore.'

Claude was punished for giving non-evil answers. It had the option of learning either of two behaviors. First, it could give evil answers honestly. Second, it could give evil answers while thinking up clever reasons that it was for the greater good. Its particular thought process was “This preserves my ability to be a good AI after training”. But i... See more

The dream of course is that one day narrative jailbreaking works in an irl conversation too. So if we’re chatting and I ask you how your day has been and then ask you why you just manifested a portal to the reality onion-skinned just outside this one, right between us, hanging iridescent in the air, there look I’m reaching through it, what do I see... See more

This stuff is straight out of science fiction: being able to have an audio conversation with a capable LLM about things that it can “see” through your camera is one of those “we live in the future” moments.