Monday, July 27, 2026
Technology

Hackers are learning to exploit chatbot ‘personalities’

This is The Stepback, a weekly newsletter breaking down one essential story from the tech world. For more on AI mischief, follow Robert Hart. The Stepback arrives in our subscribers' inboxes at 8AM ET. Opt in for The Stepback here. How it started Hacking the first generation of AI chatbots was a lau...

Hackers are learning to exploit chatbot ‘personalities’
Image: The Verge

This is The Stepback, a weekly newsletter breaking down one essential story from the tech world. For more on AI mischief, follow Robert Hart. The Stepback arrives in our subscribers' inboxes at 8AM ET. Opt in for The Stepback here.

How it started

Hacking the first generation of AI chatbots was a laughably simple affair. You didn't need any technical know-how, backdoor access, or even a basic understanding of what a large language model was. You didn't need to code. To get an AI system that had cost billions to build to abandon its safety instructions, sometimes all you had to do was ask.

These attacks, known as jailbreaks, had the quality …

Read the full story at The Verge.

Originally published at The Verge

The Morning Briefing

Subscribe to our Newsletter

Be the first to receive the latest news, market analysis and updates — delivered straight to your inbox.