OpenAI details efforts to secure its ChatGPT Atlas browser against prompt injection attacks, including building an “LLM-based automated attacker” (Rebecca Bellan/TechCrunch)

Rebecca Bellan / TechCrunch:
OpenAI details efforts to secure its ChatGPT Atlas browser against prompt injection attacks, including building an “LLM-based automated attacker”  —  Even as OpenAI works to harden its Atlas AI browser against cyberattacks, the company admits that prompt injections …