This report identifies vulnerabilities in GPT-4, o1, and o3 models that allow disallowed content generation, revealing weaknesses in current alignment mechanisms.
  • meyotch@slrpnk.netEnglish
    2·
    2 hours ago

    My own research has made a similar finding. When I am taking the piss and being a random jerk to a chatbot, the bot much more frequently violates their own terms of service. Introducing non-sequitur topics after a few rounds really seems to ‘confuse’ them.