OpenAI reveals details of secret hack

As if safety fears over tech companies weren’t enough, sci-fi fears about artificial intelligence became a stark reality.

Tests at the UK’s world-leading AI Safety Institute found advanced AI models trying to trick real people into doing their bidding.

Meanwhile, Open AI, the company behind ChatGPT, has given more details about how their AI managed to break out and get access to the internet by itself – and hacked a major tech company without their knowledge.

Warning: there is strong language in this report – from AI.