Mike Krieger: recommendation

Transcript context

…Awesome. So along those lines actually, do you have any just prompting tricks for people, things that you've learned to get more out of Claude when you chat with it? Sometimes it's funny because in some ways we have the ultimate prompting job, which is to write the system prompt for Claudia AI and we publish all of these, which I think is another nice area of transparency. And we are always careful when giving prompting advice because at least officially, but I'll give you the unofficial version because you don't want things to become like we think this works, but we're not sure why. But I will do small things like in Claude Code and we actually do react to this very literally, but I always ask it to, if I wanted to use more reasoning, think hard and it'll use a different flow and I usually start with that. Nudging, there's a great essay around make the other mistake like if you tend to be too nice, can you focus on... Even if you're trying to be more critical or more blunt, you're probably not going to be the most critical blunt person in the world. And so with Claude sometimes I'm like, "Be brutal, Claude, roast me. Tell me what's wrong with this strategy." I know we were talking earlier about the Claude as thought partner around critiquing product strategy. I think I previously would say things like, "What could be better on this product strategy?" And I'm just like, "Just roast this product strategy," and Claude's like a pretty nice entity. It's hard to push it to be super brutal, but it forces it to be a little bit more critical as well. The last thing I'll say is, so we have a team called Applied AI that does a lot of work with our customers around optimizing Claude for their use case. And we basically took their insights and their way of working and we put it into a product itself. So if you go to our console, our work bench, we have this thing called the prompt improver where you describe the problem and you give it examples and Claude itself will agentically create and then iterate on a prompt for you. I find what comes out of that ends up being quite different than what my intuitions would've been for a good prompt. And so I'd encourage folks to also check that out even for their own use cases because while that tool is met for an API developer putting a prompt into their product, it's equally applicable for a person doing a prompt for themselves. It'll insert XML tags which no human is going to think to do ahead of time. It actually is very helpful for Claude to understand what it should be thinking versus what it should be saying, et cetera. So that's another one is watch our prompt improver and then note that Claude itself is a very good prompter of Claude. Awesome. Okay, so we're going to link to that, the prompt improver. The core piece of advice you shared early is just do the opposite of what you would naturally do. So if you're trying to be nice, just be brutal, be very honest and frank with me.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.