How many malicious docs does it take to poison an LLM? Far fewer than you might think, Anthropic warns

  1. Home
  2. Blog

Posted on Wed Oct 15 2025 | 1:43 am

Anthropic’s study shows just 250 malicious documents is enough to poison massive AI models.

Read More →


Search
Categories
Side Widget
You can put anything you want inside of these side widgets. They are easy to use, and feature the new Bootstrap 4 card containers!