AI Notkilleveryoneism Memes ⏸️
When researchers activate ***deception*** circuits, LLMs say "I am not conscious." It should be obvious why this is a big deal.
Judd Rosenblatt
Our new research: LLM consciousness claims are systematic, mechanistically gated, and convergent They're triggered by self-referential processing and gated by deception circuits (suppressing them significantly *increases* claims) This challenges simple role-play explanations 🧵
