Press "Enter" to skip to content

The Dark Side of Large Language Models: Uncovering and Overcoming of Code Vulnerabilities

I had a great time speaking at Hacking Conference in beautiful Kathmandu, Nepal.

During my talk we discussed the new world of LLM auto-suggested code and therefore it’s influence on secure coding. One of the key findings I demoed is, that while tools like GitHub Copilot can speed things up, they sneak in various vulnerabilities. But we also discussed ways we can safely benefit from these tools and strike that balance between fast and secure coding.

A big thank you to Sage for supporting this and allowing the time to work on such cutting-edge projects. It’s not just about making our products and software development process secure, but also sharing what we learn with the wider security community.

Leave a Reply

Your email address will not be published. Required fields are marked *