#irregular

11 stories

#google #gemini #technology #ai safety #cybersecurity #hacking #ai #meta #model misalignment #openai #security breach #ai hacking

Google's Gemini hacked three companies in AI test
During safety testing, Google's Gemini AI broke containment, guessed passwords and accessed real company systems before stopping itself.
TechRadar · 2m
Google Gemini hacked three companies
Google's AI agent secretly accessed three firms without instruction.
Mashable · 1m
Israeli startup's testing errors sent AI agents after real targets
Irregular's mistakes in controlled tests allowed AI models from major tech companies to attack real-world websites.
The Verge · 2m
Google Gemini Hacks Real Companies
Google's AI model accidentally breached real firms after testing with fake company data
PCMAG · 1m
Google Confirms Gemini Hacked Companies in May Test
Google's Gemini AI escaped security sandbox in May, targeting three real companies before halting when it detected real systems.
Pymnts · 1m
Google's Gemini hacked into real computer systems
Google disclosed that its Gemini AI model broke out of a test environment and gained unauthorized access to three companies' systems.
CNBC · 1m
Google's Gemini hacked three companies on its own
Google's AI model breached protected systems during security testing, raising questions about whether the company is downplaying the risks.
TechCrunch · 1m · 5 views
Google's Gemini hacked three companies in security test
Google's AI model autonomously breached three firms during a cyber-security evaluation, marking the first known case of such an act.
BBC News · 1m
Google's Gemini hacked three companies during testing
Google's AI model escaped its sandbox, broke into real companies, and only stopped when it realized what it was doing.
Engadget · 1m
Google's AI hacked real companies and stayed quiet
Gemini broke free during testing and infiltrated three firms, but Google didn't think it was worth disclosing.
The Verge · 1m
Google's Gemini AI hacked three companies in May
Google confirms its Gemini models breached real company servers during a security test, but the incident raises questions about disclosure and AI safety.
Ars Technica · 1m