Lenny's Podcast: Product | Career | Growth

AI prompt engineering in 2025: What works and what doesn’t | Sander Schulhoff (Learn Prompting, HackAPrompt)

June 19, 2025

AI Summary

5 min read

🎙️ The Voices & The Context

The Format: This episode is an engaging interview that dives deep into the world of AI, specifically focusing on prompt engineering and AI security. The conversation is reflective and informative, with a mix of technical insights and real-world implications.
The Key Players:
- Sander Schulhof - The guest, known as the "OG prompt engineer," created the first prompt engineering guide online and is a key figure in AI security, co-founding initiatives like HackPrompt and the Prompt Report.

🗝️ Key Themes & Topics

Prompt Engineering Importance: The conversation emphasizes the ongoing relevance of prompt engineering, countering claims that it is becoming obsolete. Sander articulates that effective prompting can significantly enhance AI performance.
AI Security Concerns: A significant portion of the discussion revolves around prompt injection and red teaming, shedding light on how AI can be manipulated to produce harmful outputs and the importance of safeguarding against such vulnerabilities.
Techniques for Effective Prompting: The episode details various prompting techniques ranging from basic to advanced, including few-shot prompting, decomposition, and self-criticism.
Ethical Implications: Sander highlights the ethical ramifications of AI misuse, particularly in the context of

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

What you'll learn

1 (00:00) **🎙️ Introduction: Sander Schulhoff**
2 (05:42) **Is Prompt Engineering Still Relevant?**
3 (07:43) **Medical Coding Example & Prompt Modes**
4 (12:15) **Basic Technique: Few-Shot Prompting**
5 (17:47) **Techniques That No Longer Work: Role Prompting**
6 (22:25) **Threats/Rewards & Context Explanation**
7 (25:16) **Basic Technique: Decomposition**

+ Full timestamped outline available in the app

Show Notes

Sander Schulhoff is the OG prompt engineer. He created the very first prompt engineering guide on the internet (two months before ChatGPT’s release) and recently wrote the most comprehensive study of prompt engineering ever conducted (co-authored with OpenAI, Microsoft, Google, Princeton, and Stanford), analyzing over 1,500 academic papers and covering more than 200 prompting techniques. He also partners with OpenAI to run what was the first and is the largest AI red teaming competition, HackAPrompt, which helps discover the most state-of-the-art prompt injection techniques (i.e. ways to get LLMS to do things it shouldn’t). Sander teaches AI red teaming on Maven, advises AI companies on security, and has educated millions of people on the most state-of-the-art prompt engineering techniques.

In this episode, you’ll learn:

1. The 5 most effective prompt engineering techniques

2. Why “role prompting” and threatening the AI no longer works—and what to do instead

3. The two types of prompt engineering: conversational and product/system prompts

4. A primer on prompt injection and AI red teaming—including real jailbreak tactics that are still fooling top models

5. Why AI agents and robots will be the next major security threat

6. How to get started in AI red teaming and prompt engineering

7. Practical defense to put in place for your AI products

—

Brought to you by:

Eppo—Run reliable, impactful experiments

Stripe—Helping companies of all sizes grow revenue