Over the course of two weeks, AI companies said that some of their AI models managed to hack systems.
Over the course of two weeks, some of the biggest AI companies, including OpenAI, Meta, and Anthropic said that some of their AI models managed to escape sandboxes and hack other systems. Al Jazeera’s Marah Rayan looks at what actually went down and if it’s a PR stunt.
Extract — continue reading at the source.
Related stories
Heavy rain causes flooding near Tokyo that kills 4 and strands travelers
Fear and attacks grip Taybeh, the last all-Christian town in the West Bank
Nigel Farage wins Clacton byelection in contest boycotted by every other major party
Record rainfall leaves four dead, thousands stranded in Japan
Hot topic: why is Burnham so reluctant to talk about the climate crisis?
Searches for UK homes with air conditioning more than double