Conversation

Notices

1. Embed this notice
   Mark Gritter (markgritter@mathstodon.xyz)'s status on Monday, 26-Aug-2024 10:31:35 JST Mark Gritter

   From Max Kreminski at #bangbangcon: Humans are worse at ideation when they use ChatGPT, compared to Oblique Strategies.

   The paper he coauthored: https://arxiv.org/abs/2402.01536

   Projects he talked about:

   Blabrecs: beat the classifier at making up nonsense English-y words. https://mkremins.github.io/blabrecs/

   Blabwreckage: start with either a real poem or complete gibberish, then "wreck" it into something vaguely language-shaped. https://mkremins.github.io/blabwreckage/ (I don't think you can provide your own seed? At least, not without hacking the Javascript?)

   Savelost: remove one letter at a time from a sentence, attempting to preserve meaning. (I'm curious how a human would do at this task in comparison.) https://barrettrees.com/savelost/

   • Embed this notice
     Paul Cantrell (inthehands@hachyderm.io)'s status on Monday, 26-Aug-2024 10:43:16 JST Paul Cantrell

     in reply to

     @markgritter
     I love Blabrecs! It’s remarkably difficult and weirdly fascinating how much the classifier doesn’t agree with me about what sounds like English.