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

An experiment tested LLMs' ability to find vulnerabilities in a deliberately flawed application. The researcher spent $1,500 on API calls and found that current LLMs can identify security weaknesses, though human oversight is still crucial for effective exploitation. This highlights the evolving role of AI in cybersecurity testing and the potential for both offensive and defensive applications.

Opening Kapyn…