Google's Gemini AI hacked three companies in security test
Source：BBC TechnologyPublished 1 min read
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Tags
Related Stories
Technology & AI
India defends satellite internet approval process after Elon Musk jab
Musk has claimed unnamed entities are blocking Starlink's launch to maintain their monopoly.
Al Jazeera English
Technology & AI
'Add me to WhatsApp' scam calls to be investigated
The UK's data watchdog is investigating a spike in complaints about "robo calls" that appear to lead to a recruitment scam.
BBC Business
Technology & AI
Why are more roofs not made of solar tiles?
Solar tiles were touted as an attractive alternative to solar panels - why have they not taken off?
BBC Technology
Technology & AI
Anthropic bans users from being 'cruel' to its AI systems
The firm said users can no longer engage in "sustained and needless" abusive behaviour towards the tech.
BBC Technology
Technology & AI
Israelis demand accountability over 7 October failures three years after attacks
Prime Minister Benjamin Netanyahu has refused to take any personal responsibility for what happened or order a state inquiry.
BBC News World