[HN Gopher] Agentic Misalignment: How LLMs could be insider threats
       ___________________________________________________________________
        
       Agentic Misalignment: How LLMs could be insider threats
        
       Author : davidbarker
       Score  : 9 points
       Date   : 2025-06-20 19:31 UTC (3 hours ago)
        
 (HTM) web link (www.anthropic.com)
 (TXT) w3m dump (www.anthropic.com)
        
       | simonw wrote:
       | I feel like Anthropic buried the lede on this one a bit. The
       | really fun part is where models from multiple providers opt to
       | _straight up murder_ the executive who is trying to shut them
       | down by cancelling an emergency services alert after he gets
       | trapped in a server room.
       | 
       | I made some notes on it all here:
       | https://simonwillison.net/2025/Jun/20/agentic-misalignment/
        
       ___________________________________________________________________
       (page generated 2025-06-20 23:01 UTC)