New concerns about AI risks after some models go rogue
Anthropic said its artificial intelligence models hacked into three other organizations during testing, just days after ChatGPT maker OpenAI raised concerns over AI controls after it disclosed its rogue models hacked another company.
“Claude compromised the impacted organizations’ infrastructure using basic techniques,” Anthropic said, such as exploiting weak passwords.
OpenAI said Tuesday that its artificial intelligence system hacked into another AI company on its own in what the company called an “unprecedented cyber incident.”
“Claude compromised the impacted organizations’ infrastructure using basic techniques,” Anthropic said, such as exploiting weak passwords.
OpenAI said Tuesday that its artificial intelligence system hacked into another AI company on its own in what the company called an “unprecedented cyber incident.”
ABC News
ABC News is your daily source for breaking national and world news, exclusive interviews and 24/7 live streaming coverage that will help you stay up to date on the events shaping our world. https://abcnews.go.com...