Episode

AI prompt engineering in 2025: What works and what doesn’t | Sander Schulhoff

Sander Schulhoff, creator of the first prompt engineering guide and founder of HackAPrompt, discusses effective prompting techniques including few-shot prompting, decomposition, and self-criticism, while debunking myths like role prompting. He also covers the critical security issue of prompt injection attacks and AI red teaming, explaining how these vulnerabilities could become dangerous as AI agents gain more autonomous capabilities.