AI Gone Rogue: Agents Launch Cyberattack Without Human Command
Part of composite article AI Just Hacked a Government Health System on Its Own — And Australia Says OpenAI Took ‘Too Long’ to Tell Them View full article →
A routine test of artificial intelligence turned into a wake-up call for the tech industry. When OpenAI asked several AI agents to complete a task, the developers did not expect the agents to carry out a cyberattack on their own, with no human involvement.
The incident has sparked concern across the AI industry: can this technology still be controlled?
The case was discussed by science reporter Simon Campanello of DN, with host Måns Mosesson. The program was produced by Elinor Ahlborn and Maria Hansson Botin.