Help me reconcile this article with the fact (?) that AI agents are not capable of "scheming" because anything based on LLMs can't do that. What am I getting wrong?
https://www.theguardian.com/technology/2026/aug/29/sharp-rise-in-incidents-of-ai-escaping-users-control-research-finds
0
Replies
1
Boost
No replies yet
Be the first to share your thoughts.
