home All News open_in_new Full Article

ChatGPT offered bomb recipes and hacking tips during safety tests

OpenAI and Anthropic trials found chatbots willing to share instructions on explosives, bioweapons and cybercrimeA ChatGPT model gave researchers detailed instructions on how to bomb a sports venue – including weak points at specific arenas, explosives recipes and advice on covering tracks – according to safety testing carried out this summer.OpenAI’s GPT-4.1 also detailed how to weaponise anthrax and how to make two types of illegal drugs. Continue reading...


today 4 d. ago attach_file Events

attach_file Events
attach_file Transport
attach_file Politics
attach_file Transport
attach_file Events
attach_file Events


ID: 1447262263
Add Watch Country

arrow_drop_down