View Single Post
john70t john70t is online now
You do not have permissi
 
john70t's Avatar
 
Join Date: Aug 2001
Location: midwest
Posts: 39,937
https://www.anthropic.com/research/small-samples-poison
In a joint study with the UK AI Security Institute and the Alan Turing Institute, we found that as few as 250 malicious documents can produce a "backdoor" vulnerability in a large language model—regardless of model size or training data volume.
__________________
Meanwhile other things are still happening.
Old 10-16-2025, 06:08 AM
  Pelican Parts Catalog | Tech Articles | Promos & Specials    Reply With Quote #18 (permalink)