I specialize in stress-testing Large Language Models (LLMs) to identify security gaps and ethical vulnerabilities. Using creative adversarial prompting, I challenge AI boundaries to see if they can be manipulated into generating unsafe, biased, or illogical outputs. My goal is to help you build a more resilient and secure AI by finding its breaking points before your users do.
20 minutes
estimated duration
secure payment
payment protection via Stripe
Bantul, Yogyakarta, ID
provider location
secure checkout powered by Stripe
your payment is protected, refunded if provider declines or doesn't respond