Recursion into madness

(blog.coredump.cx)

29 points | by surprisetalk 3 days ago

6 comments

  • pattt 4 minutes ago
    It would be interesting how many iterations of LLM-based PR reviews and fixes it takes to turn the code into horror. It’s already started happening.
  • MarkusQ 51 minutes ago
    It would have been interesting to try something closer to the movie poster example; say have the AI rewrite the passage with the room toggling between the initial light-mode decor and a dark-mode decor, then back, repeatedly. Or even change the woman's name to "Mrs. Smythe" and back.
    • layer8 19 minutes ago
      As the article explains: “[…] In other words, if you instruct a model to change a single word in a paragraph of text, it can almost always handle the task with no collateral damage.“
  • Muromec 59 minutes ago
    It doesn't merely stabilise, it almost converges on itself
  • groby_b 1 hour ago
    The existence of attractors (e.g. "stable at iteration 31") for AI models is one of the weirdest things in AI land. They are a wonderful space to explore, fascinating and full of horrors.

    Meanwhile, my hat's off to the (currently) last comment on the page: "I like how the shear-sheathed legs still earned their keep — probably load-bearing for Mrs. Regan"

  • amelius 1 hour ago
    The same happens with humans, in e.g. chain stories, cumulative stories, etc.

    Not unique to AI.

  • lowbloodsugar 57 minutes ago
    >I don’t write about generative AI much. Everyone else does; not much of consequence ever gets said.

    I see he chose not to break with tradition.