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

The author built a vulnerable app to test if Large Language Models (LLMs) could hack it. They spent $1,500 on LLM services to see if the models could find vulnerabilities. The results showed that LLMs were able to find some vulnerabilities, but not all. This experiment highlights the potential risks of using LLMs for security testing. It's essential to consider the limitations and capabilities of LLMs when using them for security purposes.