Pathological Liars in a box. AI Models Mislead Users on Login URLs - Infosecurity Magazine
Never login to a bank, or other financial service with a link you get randomly off the internet. And asking an AI for the info is no better.
As Carignan concluded: “LLMs don’t ‘retrieve’ information – they generate it [...]. Without proper sourcing, these systems become ripe for both inaccuracy and exploitation.”
You think the AI is looking stuff up on the internet. It isn't.
No comments:
Post a Comment
Comment Moderation is in place. Your comment will be visible as soon as I can get to it. Unless it is SPAM, and then it will never see the light of day.
Be Nice. Personal Attacks WILL be deleted. And I reserve the right to delete stuff that annoys me.