Hacker News: Newest
shared a link post in group #Hacker News
www.anthropic.com
A small number of samples can poison LLMs of any size
Anthropic research on data-poisoning attacks in large language models
Comment here to discuss with all recipients or tap a user's profile image to discuss privately.
Embed post to a webpage :
<div data-postid="mwmgvbg" [...] </div>