Meet the AI jailbreakers: 'I see the worst things humanity has produced'
Fast facts
- Category: Business
- Language: EN
- Published: 2026-04-29 05:00 UTC
- Sources: The Guardian Business
Hackers are testing the safety and security of AI by tricking large language models into breaking their own rules. The process requires ingenuity and manipulation, and can come at a deep emotional cost.
Why it matters
- This update can influence the Business agenda over the next 24-48 hours.
- It is based on 1 source, which helps cross-check key claims quickly.
- Watch follow-up statements and market/public response to assess real impact.