LLM-generated passwords (generated directly by the LLM, rather than by an agent using a tool) appear strong, but are fundamentally insecure, because LLMs are designed to predict tokens – the opposite of securely and uniformly sampling random characters.

you are viewing a single comment's thread
view the rest of the comments
[–] 25 points 5 months ago

Welp, that's another thing I hadn't thought you could use llms for and another thing I would never do

  • source