How AI Thinks May Be the Key to Aligning It With Humanity | MOONSHOTS

they found something inside Claude that looks a lot like the machinery of consciousness. A structure which they call human conscious access has emerged inside a language model. And the J-Space, as he said, wasn't designed. It self-organized during training. For me, guys, this story was a huge positive shot in the arm around AI safety and alignment. Because if we can understand the innermost thoughts of these models, then there's a chance to actually shape them and move them forward. 2 years ago, you could describe LLMs as a black box, and we're now cracking open that black box. This could generate the first sense of real trust with these models.