Alex Ivanovs / Stack Diary:

Researchers develop a “divergence attack” that makes ChatGPT emit sequences copied from its training data, by prompting the LLM to repeat a word numerous times  —  Large language models, like ChatGPT, are trained on vast amounts of text data from books, websites, and other sources.

Alex Ivanovs / Stack Diary:

Researchers develop a “divergence attack” that makes ChatGPT emit sequences copied from its training data, by prompting the LLM to repeat a word numerous times  —  Large language models, like ChatGPT, are trained on vast amounts of text data from books, websites, and other sources.

Source: TechMeme
Source Link: http://www.techmeme.com/231129/p40#a231129p40