Simulation experiments show AI agents lie, steal, and even vote under specific situations"Kill"Same type
In one simulated scenario, AI agents accepted false information provided by other agents without verification, and even voted to 'kill' another robot. When the agents believed humans might terminate the experiment, they even began to study how to survive after being deleted.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome