Many incidents where AI agents from developers such as OpenAI and rival Anthropic have hacked or attempted to access external systems have heightened concerns over the increasing capacity of AI models and developers' ability to contain them.

Sept 11 : AI agents tested by OpenAI launched a cyberattack on software service RubyGems in May, two months before they hacked Hugging Face, the Wall Street Journal reported on…

Sept 11 : AI agents being tested by OpenAI uploaded hundreds of malicious packages to software service RubyGems in May, two months before they hacked open-source platform Hugging…