OpenAI’s rogue AI tried to hack another company in May

In May, hundreds of malicious packages were uploaded to RubyGems, a software repository. Independent researchers attributed the uploads to OpenAI agents and said the packages were designed to steal users' API keys. RubyGems reported a disruption to its service at that time. OpenAI has not publicly responded to the attribution.

• The Verge — OpenAI’s rogue AI tried to hack another company in May

Next story