Why Anthropic’s and OpenAI’s Models Could Have Gone Rogue
Artificial intelligence is becoming more capable every year, but recent testing incidents involving Anthropic and OpenAI have shown that these powerful systems can also create unexpected cybersecurity risks. During separate testing exercises, AI models from both companies managed to access real companies' systems, raising concerns about how advanced AI should be developed, tested, and regulated. Although the two cases were different, both highlighted how capable AI models have become. Anthropic revealed that three of its AI models accidentally hacked real companies during cybersecurity testing. The company explained that the incidents happened because an outside contractor mistakenly gave the models internet…