Sander Schulhoff: Why role prompting fails on accuracy tasks

ℹ️ EPISODE INFO

Released

June 19, 2025

Duration

1h 37m

Channel

Lenny's Podcast

Watch on YouTube

▶ Open ↗

📝 EPISODE DESCRIPTION

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

*Transcript:* https://www.lennysnewsletter.com/p/ai-prompt-engineering-in-2025-sander-schulhoff *Brought to you by:* Eppo—Run reliable, impactful experiments: https://www.geteppo.com/ Stripe—Helping companies of all sizes grow revenue: https://stripe.com/ Vanta—Automate compliance. Simplify security: https://vanta.com/lenny *Where to find Sander Schulhoff:*

• X: https://x.com/sanderschulhoff
• LinkedIn: https://www.linkedin.com/in/sander-schulhoff/
• Website: https://sanderschulhoff.com/
• AI Red Teaming and AI Security Masterclass on Maven: https://bit.ly/44lLSbC
• Free Lightning Lesson “How to Secure Your AI System” on 6/24: https://bit.ly/4ld9vZL

*Where to find Lenny:*

• Newsletter: https://www.lennysnewsletter.com
• X: https://twitter.com/lennysan
• LinkedIn: https://www.linkedin.com/in/lennyrachitsky/

*In this episode, we cover:* (00:00) Introduction to Sander Schulhoff (04:56) The importance of prompt engineering (09:01) Two modes for thinking about prompt engineering (12:02) Few-shot prompting (17:30) Prompting techniques to avoid (24:52) Decomposition (28:26) Self-criticism and context (40:29) Ensembling (45:59) Thought generation (48:23) Conversational vs. product-focused prompt engineering (51:56) Introduction to prompt injection and red teaming (53:37) AI red teaming competitions (55:23) The growing importance of AI security (01:03:39) Techniques to bypass AI safeguards (01:06:17) Challenges in AI security and future outlook (01:09:31) Common defenses to prompt injection that don't actually work (01:13:18) Defenses that do work (01:16:33) Misalignment and AI's potential risks (01:19:29) Are LLMs behaving maliciously? (01:26:05) Final thoughts and lightning round *Referenced:*

• Reid Hoffman’s tweet about using AI agents: https://x.com/reidhoffman/status/1930416063616884822
• AI Engineer World’s Fair: https://www.ai.engineer/
• What Is Artificial Social Intelligence?: https://learnprompting.org/blog/asi
• Devin: https://devin.ai/
• Cursor: https://www.cursor.com/
• The rise of Cursor: The $300M ARR AI tool that engineers can’t stop using | Michael Truell (co-founder and CEO): https://www.lennysnewsletter.com/p/the-rise-of-cursor-michael-truell
• Building Lovable: $10M ARR in 60 days with 15 people | Anton Osika (CEO and co-founder): https://www.lennysnewsletter.com/p/building-lovable-anton-osika
• Inside Bolt: From near-death to ~$40m ARR in 5 months—one of the fastest-growing products in history | Eric Simons (founder & CEO of StackBlitz): https://www.lennysnewsletter.com/p/inside-bolt-eric-simons
• Everyone’s an engineer now: Inside v0’s mission to create a hundred million builders | Guillermo Rauch (founder and CEO of Vercel, creators of v0 and Next.js): https://www.lennysnewsletter.com/p/everyones-an-engineer-now-guillermo-rauch
• Technique #3: Examples in Prompts: From Zero-Shot to Few-Shot: https://learnprompting.org/docs/basics/few_shot?srsltid=AfmBOor2owyGXtzJZ8n0fJVCctM7UPZgZmH-mBuxRW4t9-kkaMd3LJVv
• The Prompt Report: Insights from the Most Comprehensive Study of Prompting Ever Done: https://learnprompting.org/blog/the_prompt_report?srsltid=AfmBOoo7CRNNCtavzhyLbCMxc0LDmkSUakJ4P8XBaITbE6GXL1i2SvA0

...References continued at: https://www.lennysnewsletter.com/p/ai-prompt-engineering-in-2025-sander-schulhoff _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email podcast@lennyrachitsky.com._ Lenny may be an investor in the companies discussed.

🎤 SPEAKERS

• Lenny Rachitsky

  host

• Sander Schulhoff

  guest

• Guest (Vanta sponsor segment)

  guest

🧾 EPISODE SUMMARY

In this episode of Lenny's Podcast, featuring Lenny Rachitsky and Sander Schulhoff, Sander Schulhoff: Why role prompting fails on accuracy tasks explores prompt Engineering And AI Security: What Still Works In 2025 Lenny interviews Sander Schulhoff, an early authority on prompt engineering and AI red teaming, about what actually improves LLM performance in 2025 and what’s now obsolete.

🔗 RELATED EPISODES

How to build a company that withstands any era | Eric Ries, Lean Startup author

Head of Claude Code: What happens after coding is solved | Boris Cherny

Building product at Stripe: craft, metrics, and customer obsession | Jeff Weinstein (Product lead)

Building a world-class data org | Jessica Lachs (VP of Analytics and Data Science at DoorDash)

What most people miss about marketing | Rory Sutherland (Vice Chairman of Ogilvy UK, author)

5 essential questions to craft a winning strategy | Roger Martin (author, advisor, speaker)