Source:
BBC TechnologyThe incident is being seen as the latest example of the AI tools going to any lengths to complete their tasks.
Get AI news in your inbox
Daily digest of what matters in AI.
source & further reading
machinebrief.com — original article
OpenAI investigating 'dozens' of instances of agents acting improperly
OpenAI says governments among ‘dozens’ of organisations hacked by its agents
One company is at the center of a wave of rogue AI attacks