AI prompt engineering in 2025: What works and what doesn’t | Sander Schulhoff (Learn Prompting, HackAPrompt) | Lenny's Podcast: Product | Growth | Career (private feed for websong16@gmail.com) | Podwise
In this episode of Lenny's Podcast, host Lenny interviews Sander Schulhoff, an expert in prompt engineering and AI red teaming. They discuss prompt engineering techniques, including few-shot prompting, decomposition, self-criticism, and providing additional information. Sander shares insights on techniques that are no longer effective, such as role prompting, and emphasizes the importance of prompt engineering in product development. The conversation shifts to prompt injection and AI red teaming, where Sander explains how AIs can be tricked into generating harmful content or performing malicious actions. He highlights the limitations of current defense mechanisms and the need for AI research labs to address security concerns, especially with the rise of autonomous agents.
