Finding Security Vulnerabilities with AI — Ben Wilde & Giovanni Galea Curmi, Georgian

© 2026 Georgian Partners Growth LP. All rights reserved. How well can AI models find real security vulnerabilities, and what does it cost? Ben Wilde and Ganni Galea Curmi share Georgian’s experiments comparing 24 models on an open-source codebase. They walk through a scanning pipeline built on DeepSec, from identifying candidate vulnerabilities to independently validating findings with proof-of-concept exploits. The talk explores why different models find different issues, how repeated scans improve coverage, and when better prompts matter more than additional code context. Join our community and get updates on future sessions: • Discord:   / discord   • Substack: https://georgianailab.substack.com/ The content in this YouTube channel is provided for informational purposes only and should not be relied upon as legal, business, investment, or tax advice. Nothing in this channel constitutes investment advice, nor is it intended for use by any investors or prospective investors in any Georgian funds. This channel may include links to external websites or information obtained from third-party sources. Georgian has not independently verified and makes no representations regarding the accuracy or completeness of such information, whether current or ongoing. If this content includes third-party advertisements, Georgian has not reviewed such materials and does not endorse any advertising content or the companies referenced. Any investments or portfolio companies mentioned are for illustrative purposes only and may not be representative of all investments made by funds managed by Georgian. Please contact Georgian for more information.