Comment by JumpCrisscross
8 hours ago
> With enough time (and tokens), they'll eventually recover
The article’s point is this is not true. They wind up in bullshit attractors where they hit a wall and then get lost within their muddled context window.
> they only need to succeed once
Yet they don’t. Not on their own. Like, you haven’t had an LLM get stuck in a stupid loop where you point out the flaw and then it gets unstuck?
In a ralph loop you start any iteration from scratch and feed the prompt with last X iterations in order to avoid getting stuck.