The Game of Capabilities and Security! OpenAI Launches ChatGPT Block Mode, Willing to Cut Off the Internet to Prevent Data Leaks
Generative Artificial Intelligence is evolving towards the era of agents, with enhanced tool utilization and network capabilities, posing challenges to security defenses. To address prompt injection attacks, OpenAI has introduced a 'block mode' security setting, available to all logged-in users, aimed at strengthening system protection.