The ‘WarGames’ problem: Computer science has long understood what it takes to keep AI under control

A hit 1983 movie illustrates what computer scientists have long known: If you give an AI agent a goal but don’t control what it can and can’t do, you shouldn’t be surprised by what it does.

By: Deven Desai, Georgia Institute of Technology, The Conversation

Outlets: The Conversation

Published: September 29, 2026

Words: 1,284

Last Updated: 2 weeks, 2 days ago

Body Text Preview

By Deven Desai, Georgia Institute of Technology

AI agents don’t go rogue. That’s something only humans do.

Nevertheless, a New York Times article – representative of much news coverage of AI – described an OpenAI hacking as “A.I. bots going rogue and independently spearheading a cyberattack.”

Name-brand artificial intelligence agents have been on a hacking spree in 2026. OpenAI’s software agents hacked software company Hugging Face and government sites, Anthropic’s Claude …

Create a free account to access this story and more

Join Plucky Wire to access full stories, collaborate with newsrooms, and discover content from networks around the world.

About

FAQ

Email Us