

Ian Webster
Founder of PromptFoo, specializing in AI safety and security. Contributes expertise on vulnerabilities within AI models and user protection.
Top 3 podcasts with Ian Webster
Ranked by the Snipd community

28 snips
Jul 29, 2025 • 2h 19min
The Metis List of Top AI Researchers, High Schoolers Beat AI At Math Olympiad, Apple Might Ditch Camera Bump, GPT-5 Rumors Heating Up | Ryan Petersen, Ty Haney, Antonio García Martínez, Ian Webster, Ori Eldarov, Aaron Tan
Ryan Petersen, founder and CEO of Flexport, shares insights on transforming logistics technology and his company's acquisition of Convoy’s tech. Ty Haney discusses revitalizing Outdoor Voices through community engagement, while Antonio García Martínez reveals the impact of Spindl's acquisition by Coinbase on on-chain advertising. Ian Webster highlights security challenges in generative AI, and Ori Eldarov explains how his AI-native investment bank is supporting underserved businesses. The group also humorously discusses high schoolers outperforming AI at a math Olympiad.

25 snips
Feb 28, 2025 • 52min
What DeepSeek Means for Cybersecurity
Ian Webster, founder of PromptFoo, discusses vulnerabilities in AI models and user protection, emphasizing the need for caution with DeepSeek's backdoors. Dylan Ayrey from Truffle Security highlights the security risks of AI-generated code, urging developers to ensure safety through robust training alignments. Brian Long of Adaptive focuses on the threats posed by deepfakes and social engineering, stressing the importance of vigilance as generative AI evolves. Together, they navigate the complex landscape of AI security, calling for proactive measures against emerging risks.

23 snips
Dec 2, 2025 • 25min
Why Social Engineering Now Works on Machines
Ian Webster, Founder and CEO of PromptFoo, shares insights from his experience as a former Discord engineer focused on AI agent security. He discusses how the 'lethal trifecta'—untrusted input, sensitive data, and exfiltration—leads to security incidents. Ian highlights the innovative approach of automating red-teaming with thousands of adversarial conversations to expose vulnerabilities. He also recounts lessons learned from building agents at Discord, emphasizing the importance of integrating security into the development process.


