OpenAI’s latest AI Models Have a New Safeguard To Prevent Biorisks
Image Credits:Jaque Silva/NurPhoto / Getty ImageOpenAI has announced the implementation of a new monitoring system for its advanced reasoning models, o3 and o4-mini, designed to detect and block prompts related to biological and chemical threats. According to the company’s safety report, this mechanism is aimed at preventing the models from providing instructions that could...