Y Combinator Startup Podcast
00:20:40 · Aaron Epstein, Stephen Haney
[00:20:40] S1: Uh-huh. [00:20:41] S0: And I'll switch over to the agent now and say, please address my comments in Paper. There's only one. And this will be another way that you can kind of like target. And so you can imagine having a big design and leaving all of your feedback and then just setting your agent on it, it spin. But we see a lot of folks are leaving these running overnight. They're setting up loops of an agent just generating hundreds of variations. And it's actually a challenge for us to be, like, agent scale with our servers and everything. Like, they're they're doing a lot more work than I thought they were gonna be doing. And it's so cool. And they they... Now they come in and they curate. You know, they come in, oh, that's a good idea. That's a good idea. Let me combine these things together. Yep. It's kind of this new curation design process that I think is really interesting. [00:21:20] S1: It's so cool to think about this world where you just go in, you leave a bunch of comments on the work, you go to bed, you wake up in the morning, and they're all either addressed or lots of iterations for you to choose from are just sitting there waiting for you. [00:21:32] S0: Exactly. I think it's [00:21:33] S1: really cool. It's a new world.
00:21:33 · Aaron Epstein, Stephen Haney
[00:21:33] S1: really cool. It's a new world. [00:21:35] S0: I find that it'll do things that I know, but I wouldn't have thought of because I was too busy. Mhmm. And so it kind of, like, it lets me scale myself a little bit and have more time in my day because I can just set it on these tasks that are maybe more boilerplate, or I just don't have time to do four things at once. And so let me set the agents on it to to go address it. So it's... This is 5.5. It is working through ideas now, and you'll see it iterated. It'll... It it can take screenshots, so it'll notice things like that alignment isn't... It's running right into each other. It'll fix itself Mhmm. As it goes through. [00:22:03] S1: And Yeah. That's cool. Okay. So it's actually spit back a variation here, but the alignment's little screwed up there. And it's still working. So it's not done once it gives you something. It's it's an iterative thing that's happening here. Right? [00:22:17] S0: It checks its work. Yeah. And it can do... Agents are getting better at this too all the time. [00:22:21] S1: Mhmm.
00:22:21 · Aaron Epstein, Stephen Haney
[00:22:21] S1: Mhmm. [00:22:21] S0: For instance, like, see, like, the first shot, it ran the text over the cards. It'll usually catch that and correct it. Or if it doesn't, you can just, you know, tell it, hey. Correct the the text overflow. Mhmm. Let me do this. I'm set to fit, and we'll pop back in Conductor. Please address any text overflow issues. The other thing I noticed too is is the models are always getting better, they have different strengths and weaknesses. Mhmm. And so I I often use fast models for demos like this Mhmm. And they tend to make more mistakes. And so, you know, if you're doing this for real, you're probably using something that's right at the cutting edge, and those prove to deliver, you know, better performance. [00:22:57] S1: Yeah. What are your go to models these days?
00:22:57 · Aaron Epstein, Stephen Haney
[00:22:57] S1: Yeah. What are your go to models these days? [00:22:59] S0: So Fable is a wonderful... You know, I think that's probably the best visual taste right now. Yep. It's very slow. That's why I don't use it for demos. Yeah. I use Cursor as a Composer 2.5 Mhmm. Actually a lot. It's a very good model for the speed. Quality is very good, very precise. 5.5 is still usually a pretty good balance. So I jump around. I think if I need pure taste, it's the Fable and the anthropic models in general. If I'm going for precision or I have like, hey, have 100 artboards and I need a task to go down the entire list, I might reach for the composer. It it just does a really precise job. I find cursor is a really good harness. It... It's not too lazy. It'll often spin up sub agents to get jobs done. Yeah. So I jump around a bit. So here, it gave me kinda like three different ideas. You know? And I think from here, what I would usually do, spend a little more time on exactly what I actually want out of out of it and then give it more direction. But I might start branching. I might be like, oh, I like this. I like... You know, I kind of like the list of this. That's actually very easy to read. I have kind of like... The card layout of this actually, like, featuring one card and having some other cards to the side is nice. So I might just start branching. And think the power of this is you can ask five agents to go generate five more of each, you know, and and kind of find one that really fits
00:24:10 · Aaron Epstein, Stephen Haney
[00:24:10] S1: Yeah. What you're going for. I think one of the things that's interesting is it gives you a lot of, inspiration and ideas, and then you can start branching and going down a path. But it's still the models that's doing the design, and it still has some of the hallmarks of the things that you see Yeah. Models do frequently for better or for worse. And so how do you... When you're designing and you've got this inspiration, you're like, okay. This list is interesting. I hadn't really thought of doing that. Maybe I wanna go with that. How do you then make it more your own and get out of kind of the the standard slop that a lot of them will spit out? [00:24:44] S0: Yeah. Well, I have some, like, very specific rules I can share with you. One is that models love bold. They love bold styles. And and, really, like, try to pull your font weights back. You know? It's so tempting to bold things. Just try to pull them back as light as you can get, and it'll just magically look better designed. Another thing is too many too many sizes. Models love having five, six, seven, eight different font sizes. Yeah. Try to work with three. If you get down to three... So let's let's just try it real quick on this one. If we if we bring this down to, let's see, like, like, a 500. Even that's maybe heavier than it needs to be. Same here. Like, these don't actually need to be bold. This is such a tell of a of a... This one [00:25:23] S1: up here. The care [00:25:23] S0: organized black is so heavy. Let's just pull that back, and suddenly it looks more designed already. Right. Right.
00:25:23 · Stephen Haney, Aaron Epstein
[00:25:23] S0: organized black is so heavy. Let's just pull that back, and suddenly it looks more designed already. Right. Right. [00:25:29] S1: It looks cleaner. [00:25:30] S0: It looks cleaner and more approachable. Black here too. Let's just pull that back. These are really simple tweaks that, like, you can make. The contrast here is pretty good. A lot of times models screw up contrast. Yep. So I would... That's another step. You can just make sure it's like, is the text readable? [00:25:44] S1: Right. [00:25:44] S0: These these little two, three, four, these are a little too contrasty for my taste. I would probably pull these these back. They're supposed to be a [00:25:51] S1: supporting delete them? I mean, those are the kind of things where the models like to add numbers or little icons or things like that there. And, yeah, it's really cool that you can just go through and delete it, and it just snaps everything else up rather than leaving a blank space there.