Mazdak ( Mazdak@lemmy.org ) M to Technology - Lemmy.org@lemmy.org · 11 months agoOpenAI details efforts to secure its ChatGPT Atlas browser against prompt injection attacks, including building an “LLM-based automated attacker”techcrunch.comexternal-linkmessage-square0linkfedilinkarrow-up11cross-posted to: firefox@fedia.io
arrow-up11external-linkOpenAI details efforts to secure its ChatGPT Atlas browser against prompt injection attacks, including building an “LLM-based automated attacker”techcrunch.comMazdak ( Mazdak@lemmy.org ) M to Technology - Lemmy.org@lemmy.org · 11 months agomessage-square0linkfedilinkcross-posted to: firefox@fedia.io