A New Trick Reveals AI Models’ Inner Thoughts
Summary
A New Trick Reveals AI Models’ Inner Thoughts
Shared on Bluesky by 2 AI experts
-
1. This is a very interesting story. But this is not a matter of researchers learning how to understand what the LLMs are doing. It is researchers learning how to get around the companies’ attempts to hide what the LLM…
View on Bluesky →
Originally reported by wired.com
Read the original article →Original headline: A New Trick Reveals AI Models’ Inner Thoughts