Sander Schulhoff
Sander Schulhoff is an AI researcher specializing in AI security, prompt injection, and red teaming. He wrote the first comprehensive guide on prompt engineering and ran the first-ever prompt injection competition, working with top AI labs and companies. His dataset is now used by Fortune 500 companies to benchmark their AI systems security, he’s spent more time than anyone alive studying how attackers break AI systems, and what he’s found isn’t reassuring: the guardrails companies are buying don’t actually work, and we’ve been lucky we haven’t seen more harm so far, only because AI agents aren’t capable enough yet to do real damage.
Overlay: Building AI Products Skills
The most effective way to improve model output is to provide concrete examples of the desired result rather than relying on abstract descriptions.
"But if there were one technique that I could recommend people, it is few-shot prompting, which is just giving the AI examples of what you want it to do. So maybe you wanted to write an email in your s..."
Prompt engineering remains a critical and durable skill because even the most advanced models exhibit massive performance swings based on how they are instructed.
"Studies have shown that using bad prompts can get you down to 0% on a problem, and good prompts can boost you up to 90%. People will always be saying, 'It's dead,' or, 'It's going to be dead with the..."
Formatting prompts using structures prevalent in the training data—such as XML or clear Q&A headers—helps the LLM better interpret and execute complex instructions.
"My main advice there is choose a common format. So XML, great. If it's, I don't know, I don't know, question, colon, and then you input the question, then answer, colon, and you input the output, that..."