Raymond Chandler Rewritten by AI 31 Times Turns Noir into Body Horror
Recursion into Madness
A security researcher tests whether recursive AI self-feeding corrupts text as it does images. Feeding a Raymond Chandler passage to Gemini with the prompt to "boldly rewrite" it, then repeating the process on each output, he watches metaphors spiral from "vast, towering tomb of bleached opulence" to Mrs. Regan as "pure, unapologetic malice" before stabilizing at iteration 31 into a horror scene. The experiment shows open-ended rewrites drift into peak LLMese, not model collapse.
The room turned its opulence into a weapon, stripping away every trace of human warmth. Blinding, clinical light scorched pristine silk, razor-honed chrome, and spotless carpet. Beyond the glass, a bruised storm raged; within, leaded crystal and mirrors shattered the glare into jagged shards.
- abecedarius
This reminded me of a story/vignette which my fallible memory tags as by someone like Twain or Poe, about an automatic rewriting machine. It was put to work on the same passage with an ever higher intensity setting, becoming more and more gothic to the point of parody -- iirc the final output was verse including the line "to atoms dash the doubly damned".
Does anyone remember this?
- blargey
Speculated to be responsible for the "AI restaurant-menu gore" that made the rounds on social media. Restaurants AI-generate the entire menu sheet from whole cloth, and while it looks "good" at first with modern image models, repeated edits to the menu text/layout transform the passable food "photos" into trypophobia-inducing horrors. (And somehow they don't notice or care)
Notably, the recent ChatGPT Images 2.5 announcement claimed to address this issue specifically ("multi-turn editing consistency")
- jrochkind1
> PS. For obvious reasons, this post will fail Pangram tests.
Actual pangram to me says it's 100% human. Current pangram can flag different passages differently, but these are all flagged human by it, even the LLM written ones.