Wildly misleading. Access conscious =\ “Claude’s consciousness.”
Let’s not attempt to frame improvements in interpretability as evidence of consciousness.
LLMs are fundamentally incapable of human-like intelligence and consciousness as we mean it.
🚨BREAKING: Anthropic found access to what looks like Claude’s consciousness
New research: the “J-space”
>claude has internal thoughts it doesn’t say out loud
>mirrors human consciousness
>anthropic can now read them
Anthropic’s focus on interpretability is what’s helping them train and RL models like Mythos