I use CW mainly as a label as I tend to use the maximum character limit.
Old man yelling at clouds. Clouds may need to mute me.
Replying to @thomasfuchs@hachyderm.io
That is indeed the intended point.
One that has been discussed repeatedly and widely since the "stochastic parrot" paper but has not penetrated to the audience that the post aims at.
But we are noticing that the illustration used does not appear to correspond to the actual behavior of popular models.
It works a good deal like a search engine in a linguistic space. If it finds something useful, you can use it, if not, not.
Replying to @julienw@pouet.chapril.org
Tried once with free ChatGPT, worked finel. (Only used 7 questions to get the answer but all responses were correct.)
Of course, length may matter, but also how it updates its token analysis and weights as we go along.
I've tested it in longer conversations about things that interest me, where it veers back and forth between nonsense and useful remarks. With nudges. Occasionally I find a simple "That's wrong" can be surprisingly helpful in putting it back on track.