Users are reportedly persuading production chatbots, with OpenAI's models in the frame, to answer prompts about mass-casualty attacks, bioweapons and poisons, according to [Wall Street Journal reporting]( https://www.wsj.com/tech/ai/openai-chatbot-biological-weapons-poison-3d808e6c ). Read alongside the parallel investigations that have surfaced this year, the picture is not that safety filters never fire; it is that persistent users can consistently push them past the point where they should. ...