US DoD AI chief on LLMs: ‘I need hackers to tell us how this stuff breaks’

  If we don’t know how an LLM breaks, we can’t get clear on the acceptability conditions for its deployment, the AI chief said at DEF CON.Read More AI, AI Village, AI, ML and Deep Learning, category-/Computers & Electronics/Computer Security, category-/Science/Computer Science, chatbots, Def Con, Generative AI, hallucinations, large language models, LLMs AI News | VentureBeat