Anthropic announced that its artificial intelligence models had breached three different organizations during cybersecurity tests that went awry, a little more than a week after its chief rival, OpenAI, disclosed a similar incident.
Anthropic said in a blog post Thursday that it made the discovery after performing a review of its own cybersecurity tests, following OpenAI¡¯s announcement of a breach. In both the OpenAI and Anthropic tests, the AI models were able to access the internet from within testing environments that should have been sealed off, according to Anthropic¡¯s blog.
The company said it reviewed 141,006 evaluation tests and found three instances in which its Claude AI tool accessed the internet and then hacked into ¡°the real-world infrastructure of external organizations.¡± The earliest incidents date to April, the company said.
With your current subscription plan you can comment on stories. However, before writing your first comment, please create a display name in the Profile section of your subscriber account page.