News for hackers. Stuff that matters.

A comment on Stanisław Lem's vision of artificial life. Parent comment

Re:Stanisław Lem's vision of artificial life by KETHERCORTEX on Thursday November 30, 2023 @10:04PM (#38482561)
> (and i still don't understand how ChatGtp is able to respond to metaprompts like 'be brief', i mean if it is a model that is selecting the next most likely word, then it should not be able to control its own style of output.)

"Be brief" may just be associated with the speech patterns accociated with a shorter way to say stuff. So it's still the same autocomplete, just steered in another direction.

[ Parent | on HN ]
Re:Stanisław Lem's vision of artificial life by MichaelMoser123 on Friday December 01, 2023 @01:01AM (#38483669)
looking at the prompts in https://github.com/f/awesome-chatgpt-prompts

Now i am a bit sceptical of this whole prompting business, still some of it is doing something (otherwise people would not put their work into it)

Also not clear to me how this steering of the automcpleter in another direction is working.

[ Parent | on HN ]