62
A small number of samples can poison LLMs of any size
(www.anthropic.com)
"We did it, Patrick! We made a technological breakthrough!"
A place for all those who loathe AI to discuss things, post articles, and ridicule the AI hype. Proud supporter of working people. And proud booer of SXSW 2024.
It's hard to please everybody with an answer when you also train off the responses from said answers.
For anyone interested, Computerphile did an episode about sleeper agents in models.
Sleeper Agents in Large Language Models - Computerphile