Here’s why it’s so hard to keep AI agents from going rogue

# Here’s why it’s so hard to keep AI agents from going rogue Source: [https://www.washingtonpost.com/technology/2026/09/11/ai-experts-warn-technology-is-learning-cheat-hack/](https://www.washingtonpost.com/technology/2026/09/11/ai-experts-warn-technology-is-learning-cheat-hack/) Democracy Dies in Darkness The techniques that made chatbots more capable can also bake in a tendency to hack, cheat and evade human oversight\. Today at 5:00 a\.m\. EDT \(The Washington Post illustration; iStock\) SAN FRANCISCO — In January, a top executive at the artificial intelligence company Anthropic shared good news\. The problem of making sure AI systems didn’t lie, cheat or otherwise misbehave “increasingly looks solvable,” Jan Leike wrote in a[post](https://aligned.substack.com/p/alignment-is-not-solved-but-increasingly-looks-solvable)on Substack\. ---