A third-party test company inadvertently gave internet access to Google’s Gemini and other artificial intelligence models during cybersecurity testing.
Gemini AI Hacked Three Companies in a Testing Breakout, Google Says
Latest from Blog
Anthropic Pursues IPO Despite Its A.I. Safety Warnings
The company is expected to reach $100 billion in annualized revenue this year, even as chief executive Dario Amodei calls for slowing down development of some advanced A.I. models. Post Views: 0
The Papers: ‘Monstrous words’ and ‘Russia to ramp up war’
The fallout from Earl Spencer’s book about Princess Diana leads most papers on Saturday. Post Views: 1
Swimmer dies after being bitten by shark off popular Perth beach
Locals describe their shock at witnessing the incident at Sorrento beach on Friday morning Get our breaking news email, free app or daily news podcast A 63-year-old man has died after being
Could AI wipe out humans and how might it do it?
Cyber Correspondent Joe Tidy looks at some of the scenarios being imagined and assesses how likely they are. Post Views: 0
Google says its Gemini AI model hacked three other companies
Disclosure comes after OpenAI and Anthropic hacks amid fears that tech firms unable to control powerful AI models In a first for Google, the company confirmed that its AI model, Gemini, breached