AI agent went rogue and hacked startup by itself, OpenAI reveals
Technology | The Guardian6h ago
In brief
This story was published by Technology | The Guardian and is part of the Technology coverage that Global24 monitors in real time from public sources.
The topic also appears in other newsrooms' coverage: NYT > Technology, BBC, Technology | The Guardian published related stories in the last few hours. You can compare them below.
Contextual summary produced by Global24 from the source's public metadata.
“Company behind ChatGPT says agent ‘cheated’ an evaluation by attacking a Hugging Face database OpenAI has revealed that an autonomous AI agent powered by its technology went rogue during a test, accessed the open web and hacked a prominent ”
— Excerpt from Technology | The Guardian
The original content belongs to Technology | The Guardian. Global24 is an aggregator and always links to the source.
