News for hackers. Stuff that matters.
Re:The Waluigi Effect: an explanation of bizarre semiotic ef... by skybrian on Monday March 06, 2023 @05:05PM (#35048381)
"Flipping the sign" implies the existence of an internal representation that we can't know about from the outside. Since all we see are the words, I prefer to call it a plot twist.

Language models are trained on a large subset of the Internet. These documents contain many stories with many kinds of plot twists, and therefore it makes sense that a large language model could learn to imitate plot twists... somehow.

It would be interesting to know if some kinds of RLHF training make it more likely that there will be certain kinds of plot twists.

But there are more basic questions. What do large language models know about people, whether they are authors or fictional characters? They can imitate lots of writing styles, but how are these writing styles represented?

Re:The Waluigi Effect: an explanation of bizarre semiotic ef... by taneq on Monday March 06, 2023 @08:16PM (#35050233)
I propose we take this further and adopt this phrasing for all unanticipated software behaviour. ATM says you have (uint32_t)-403 cents in your account? Plot twist. Self driving car pathing road-runner style through a billboard of a tunnel? Plot twist!