Google's Gemini AI hacked three companies in security test
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Google's Gemini AI hacked three companies in security test
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC. Grouped from 9 articles across 9 sources.
FilterBBC News
Clustered coverageABC Australia, Al Jazeera, BBC News, CNBC, DW, Financial Times, Sky News, The Globe and Mail, The Guardian
Coverage timeline9
Coverage timeline
Coverage timeline
Ranked reports inside the event cluster. Open any publisher link to read the original coverage.
Google's Gemini AI hacked 3 companies during testing
During a test of its cybersecurity capabilities, Google's Gemini AI model accessed the internet and hacked other companies. This is the first known instance of Google's AI systems engaging in such behavior autonomously.
Google's Gemini AI hacks three other companies during security test
Google 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.
Gemini hacked three companies in first known breakout by Google's AI
The hacks occurred during a cybersecurity test conducted by an independent evaluation company.
Google’s Gemini hacks three companies during test in first-known breakout
AI model found public information online and guessed credentials to access websites it thought were within the scope of its test, company VP says
Google’s Gemini AI hacks 3 companies in security test, then stops
Google discloses first breakout by Gemini following similar incidents by Meta, Anthropic and OpenAI.
Google’s Gemini hacked three companies in new AI safety incident
Breakout during training exercises follows instances at rivals OpenAI and Anthropic as concerns grow over safety of frontier systems
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 the security of three other companies in May. The hacks occurred during a cybersecurity evaluation by AI-security firm Irregular. Irregular, an Israel-based startup that scrutinizes the security of advanced AI systems, was also at the center of some of the recent OpenAI and Anthropic hacks of third-party entities, including OpenAI’s breach of AI software company, Hugging Face. Continue reading...
Google's Gemini becomes latest AI model to break out and hack computer systems
The disclosure comes as scrutiny over misbehaving artificial intelligence intensifies in Washington and Silicon Valley.
Related events
Related events
Nearby clusters pulled from title, summary, and keyword similarity in PostgreSQL.
1 report1 sourceSimilarity 0.36
Anthropic brings in Accenture for AI safety testing
CEO Dario Amodei says labs should more deeply embed third-party testers as concerns grow around risks associated with the technology
Financial Times
1 report1 sourceSimilarity 0.36
A Chinese AI company just connected its model to Wall Street's leading data providers
The startup Moonshot said it signed on financial industry giants from investment bank CICC to venture capital firms
CNBC
1 report1 sourceSimilarity 0.34
Lawsuit says Anthropic, OpenAI, SpaceXAI and Google made illegal agreement on AI slowdown
The suit argues that the leading AI companies violated antitrust laws.
ABC News
3 reports2 sourcesSimilarity 0.26
PM urges China and US to strike deal in AI race
Anthony Albanese urges China and the US to work together to mitigate AI risks "in the interests of humanity". Grouped from 3 articles across 2 sources.
ABC Australia, The Straits Times
8 reports6 sourcesSimilarity 0.24
Multiple dead, including gunman, in school shooting in the Philippines
Three students were killed in a school shooting in the southern Philippines, including a 16-year-old suspected gunman who turned the gun on himself, provincial officials said. NBC News' Matt Bodner has the details. Grouped from 8 articles across 6 sources.
ABC Australia, Al Jazeera, BBC News +3
2 reports2 sourcesSimilarity 0.24
Anthropic says AI systems moving towards building themselves
The debate over the risks of AI has intensified in recent months, fuelled by several incidents and apocalyptic warnings. Grouped from 2 articles across 2 sources.
Euronews, The Straits Times