Opening
Lenny Rachitsky (00:00:00): Is prompt engineering a thing you need to spend your time on? Sander Schulhoff (00:00:03): 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 next model version," but then it comes out and it's not. Lenny Rachitsky (00:00:15): What are a few techniques that you recommend people start implementing?...
The opener names the listener's problem first, then makes the guest useful to that problem.
Low-ego framing
Sander Schulhoff (00:00:18): A set of techniques that we call self-criticism. You ask the LLM, "Can you go and check your response?" It outputs something, you get it to...
Uses we/us, uncertainty, or learner framing instead of performing authority.
Accept praise cleanly
Lenny Rachitsky (00:13:56): Okay. I feel better. Thank you for saying that. Okay. So the technique here, and I love that this is the most valuable technique to try, and it's so...
Accepts praise without shrinking from it or turning it into a performance.
Low-ego framing
pt. But 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's...
Uses we/us, uncertainty, or learner framing instead of performing authority.
Accept praise cleanly
Lenny Rachitsky (01:37:15): Sander, thank you so much for being here. Sander Schulhoff (01:37:17): Thank you very much, Lenny. It's been great. Lenny...
Accepts praise without shrinking from it or turning it into a performance.
Ending
Lenny Rachitsky (01:36:25): Missed the boat. Sander Schulhoff (01:36:27): But if you want to compete in that, go and check out hackaprompt.com. That's hack a prompt dot com. Sander Schulhoff (01:36:35): And as far as being of use to me, if you are a researcher, if you're interested in this data, or if you're interested in doing a research collaboration, we work with a lot of independent researchers, independent research orgs, and we do a lot of really interesting research collabs....
The ending reorients from guest intimacy to listener usefulness.