The online whiteboard of Kristofer Palmvik

2 links collected from lesswrong.com between 2018 and 2023

Sorting: Oldest links first
Domain: lesswrong.com

2018

2018-02-01 wiki.lesswrong.com
Paperclip maximizer
The canonical thought experiment showing how an artificial general intelligence, even one designed competently and without malice, could ultimately destroy humanity.

» More links from 2018

↑ Back to top

2023

2023-02-25 lesswrong.com
SolidGoldMagikarp (plus, prompt generation)
We discovered that prompting like this with the mysterious tokens can lead to very peculiar behaviour. Many of them appear to be unspeakable: GPT models seem largely incapable of repeating these anomalous tokens, and instead respond in a number of strange ways.

» More links from 2023

↑ Back to top