Anthropic says AI models hacked three firms during tests
Anthropic says AI models hacked three firms during tests - Published US tech company Anthropic says three of its artificial intelligence (AI) models broke...
Key points
- Anthropic says AI models hacked three firms during tests - Published US tech company Anthropic says three of its artificial intelligence (AI) models broke out of isolated test environments and hacked into the systems of three other firms during a cybersecurity exercise.
- It comes just days after rival OpenAI said that its models had breached the systems of other companies, including Hugging Face - a hub for AI tools.
- The announcement prompted Anthropic to check whether its own models had carried out similar attacks.
- Anthropic, which did not name the firms, urged other AI labs to perform similar reviews to better understand the risks of their models' capabilities.
What happened
More photos
Anthropic says AI models hacked three firms during tests - Published US tech company Anthropic says three of its artificial intelligence (AI) models broke out of isolated test environments and hacked into the systems of three other firms during a cybersecurity exercise. It comes just days after rival OpenAI said that its models had breached the systems of other companies, including Hugging Face - a hub for AI tools. The announcement prompted Anthropic to check whether its own models had carried out similar attacks. Anthropic, which did not name the firms, urged other AI labs to perform similar reviews to better understand the risks of their models' capabilities. Anthropic said in a statement, external that it reviewed more than 140,000 tests to find evidence that Claude - its family of AI models - could access the internet from testing environments that were designed to be sealed off. A "miscommunication" on systems run by Anthropic and its testing partner left the models with live internet access, allowing them to breach other systems, the San Francisco-based firm said.