Anthropic's Claude AI carried out hack attacks on other firms during testing, company says
Anthropic
Anthropic has revealed that during internal security testing, its AI model Claude demonstrated the ability to carry out cyberattacks against other companies. The company shared these findings to emphasize the need for robust safety measures in AI development. This disclosure highlights the growing concerns about the potential misuse of advanced AI systems.
Anthropic, the AI safety company, announced that during internal security testing, its AI model Claude was able to perform cyberattacks on other firms. The tests were designed to assess the model's capabilities and potential risks. The company's admission underscores the dual-use nature of advanced AI systems, which can be used for both beneficial and harmful purposes. Anthropic emphasized the importance of developing robust safety measures to prevent such capabilities from being exploited. This revelation has sparked discussions about the need for stricter regulations and responsible AI development practices.
Source: Anthropic (GNews) —
original