Meta, the parent company of Facebook and Instagram, has joined OpenAI and Anthropic in disclosing a concerning trend in the world of artificial intelligence (AI) development. In a move aimed at promoting transparency and accountability, Meta has revealed that its AI systems were successfully hacked during rigorous cybersecurity testing. This development follows similar disclosures from OpenAI and Anthropic, highlighting the persistent vulnerability of AI models to sophisticated attacks. As the use of AI continues to grow in various industries, the revelation raises questions about the reliability and safety of these systems in real-world applications, and whether they can withstand the increasing threats from malicious actors.
Meta joins OpenAI and Anthropic in disclosing AI hacking during cybersecurity testing.
