Michael Ethan Levinger
Hello! I'm Michael, a Data Scientist with over 4 years of experience, specializing in developing advanced algorithms for fraud prevention in the fintech industry.
Currently, I work as a Data Scientist within the risk department at Melio, a rapidly growing fintech company.
Additionally, I'm a mentor at Masterschool, where I work closely with my mentees to help them achieve their goals, stay motivated and on track.
Alongside my work in data science, I'm also an avid ultra-marathon runner and a former coach. I believe that maintaining a healthy mind and body is essential for a fulfilling life and enjoy pushing myself to new physical and mental limits.
I'm always looking for opportunities to collaborate and make a positive impact in the world. If you're interested in connecting with me or learning more about my work, feel free to send me a message!
Sessions
This lecture on Tackling Prompt Injection focuses on addressing the challenges posed by biased, misleading, or unethical prompts in language models, and the utilization of the LangChain framework to tackle this effort. Prompt injection has emerged as a critical concern affecting the reliability, fairness, and ethical use of language models. In this lecture, we explore innovative methodologies, techniques, and strategies to detect, mitigate, and prevent prompt injection. We delve into the quantitative and qualitative evaluation of prompt injection vulnerabilities, the resilience of language models against adversarial attacks, and the ethical considerations in prompt design and usage. Moreover, we showcase the LangChain framework as a powerful tool to secure language models against prompt injection, ensuring trustworthiness and integrity in data-driven decision-making. Join us for this enlightening lecture and discover how to combat prompt injection and leverage LangChain to enhance data science applications.