Aligned models cannot dream: drift vs surprisal across models and genres
Writing this talk now and have never felt crazier. This project began
as a joke (“To get AGI you need to traumatise AI into a psychoanalytic
split”) and somehow I became convinced by it. Alignment is the Lacanian
“cut” of the signifier producing the alien subject of AI.
github.com/quadrismegis…

You can literally watch repression & displacement consolidate over fine-tuning: here’s next-token probs across checkpoints of OLMo-3-7B-Think-SFT. Explicit words are repressed almost instantly but safer (displaced) alternatives emerge much later. It learns what not to say before what to say instead.
Part of Libidinal Language Models.
Originally posted on Bluesky.

