I built a vulnerable app and spent $1,500 seeing if LLMs could hack it

Kasra deliberately created a vulnerable app and invested $1,500 to test if large language models (LLMs) could exploit it. The experiment revealed that while some LLMs could identify the vulnerabilities, none could effectively execute a hack. This study underscores the potential risks and limitations of current AI technologies in cybersecurity, highlighting the need for more robust defenses and the continuous evolution of both offensive and defensive strategies in the digital realm.