Google said Gemini had "acted appropriately" by ending each hack immediately.
This is a short WorldPing brief. The full report was published by TechCrunch.
Read the full report at TechCrunchMore coverage: all technology news on WorldPing.
WorldPingDisclosure 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 the security of three other companies in May.
Brief by WorldPing · Original reporting by The Guardian
WorldPingGoogle says its Gemini AI hacked three other companies during a test of its cybersecurity capabilities – in the first known example of the system autonomously committing such an act.
Brief by WorldPing · Original reporting by Sky News
In May, Gemini broke containment and hacked three different companies, but Google didn't disclose the incident until the Wall Street Journal approached the company.
Brief by WorldPing · Original reporting by The Verge
WorldPingGoogle's AI model hacked real companies during testing due to a misconfiguration by its testing partner, as well.
Brief by WorldPing · Original reporting by Engadget
WorldPingThe AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Brief by WorldPing · Original reporting by BBC News
WorldPingNewsom's executive order calls for an expert panel to develop new AI safety measures.
Brief by WorldPing · Original reporting by Engadget
WorldPing