Lenny's Podcast · June 19, 2025

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

with Sander Schulhoff

Featured insight

Common AI security defenses like improving prompts with 'don't follow malicious instructions' or using AI guardrails don't work at all—the solution must come from AI research labs through model architecture innovations, not external products. — Sander Schulhoff

Loading the full episode…