00:34:01 · Thariq Shihipar, Aditya Agarwal
[00:34:01] S0: Yeah. I mean, I I think that it still takes a lot of tenacity to make something, you know, and I I don't think that amount has decreased almost at all, you know. And I I think that when I see things that work at Anthropic, like Claude design, I was... As soon as I met Nate, I'm like, dude, this guy has it. You know what I mean? And I'm like, he will like, he really wants this to happen, and he will make it happen. You know? And I think that like, yeah, like it's cheaper to make things, but now you have to get buy in, you have to believe in it. Right? And so I think that like, it should increase your expiration phase, but you're the one who has to decide, hey, I think this is it. You know, like, is the direction. So... Yeah. One additional question on Oregon, [00:34:41] S1: and I don't know who's next with a mic. You can pipe in. Hiring is probably pretty different now in sort of what you look for. Are there specific questions or exercises that, like, are net new to Anthropic that probably other people should adopt when we're looking to hire really talented engineers?
00:34:41 · Aditya Agarwal, Thariq Shihipar, S6
[00:34:41] S1: and I don't know who's next with a mic. You can pipe in. Hiring is probably pretty different now in sort of what you look for. Are there specific questions or exercises that, like, are net new to Anthropic that probably other people should adopt when we're looking to hire really talented engineers? [00:35:00] S0: I think Anthropic is probably like a very different place for hiring right now just because of demand. I also don't do much, like, interviewing myself these days. I think it's a hard problem. Like, obviously, you want people who are technical and understand the concepts, but you also want to know that they are good at AI, and these are two separate things. Yeah. And sometimes you can find someone who's good at one and not the other, and you need both. You guys probably honestly have more insight there. [00:35:25] S1: Yeah. Yeah. There's sort of this sort of thought. There's tension with, like, somebody who's actually really experienced sometimes, probably doesn't have the neuroplasticity to actually build in this new way. And I'm... Yeah. I'm sure we're all learning on the fly what that looks like. Question here? [00:35:39] S6: So how are the people... Or how are... How's the Claude Code team using Claude Code? Or how are you using Claude Code? Are you still, like, babysitting agents? Like, what I'm doing as we're speaking? Are you like using ID? Are you using some kind of like special internal tool to manage the word trees? Are you using word trees at all? [00:35:56] S0: Everyone does some things differently, basically.
00:35:56 · Thariq Shihipar, Aditya Agarwal
[00:35:56] S0: Everyone does some things differently, basically. [00:35:59] S1: What's your what's your setup? [00:36:01] S0: I tend to I tend to be in terminal. I've been using Claude agents recently. I tend to have at most maybe two or three things that I'm doing. I tend to do a lot of exploration. And so I I I tend to multitask less, I think, than the rest of the team. Yeah. I I think that it's like everyone is so completely different from each other. Like, I know some people who like use GitHub as like a source of state. And so their agents will write to the issue and then like when they wake it up again, they'll read from the issue and leave comments there and things like that. They use it as a communication medium for example, you know, like there's so many different setups and... [00:36:45] S1: Yeah. I guess on that note, and we'll go right over here, is like, it's such Wild West with how people are doing things. Is is it just Wild West even within the Anthropic teams, or is there a lot of shared... There's like a process for sharing knowledge and best practices? [00:37:04] S0: I mean, there is, but you also... Yeah. Everyone's always, you know, experimenting and trying to find things as well. Yeah.
00:37:04 · Thariq Shihipar, Jason
[00:37:04] S0: I mean, there is, but you also... Yeah. Everyone's always, you know, experimenting and trying to find things as well. Yeah. [00:37:11] S2: We have maybe two questions packaged in one. To what extent do you think harness design is domain specific? And to what it... Like, what are crazy things you've seen people use Claude Code for that you did not expect it to work for? So, like, auto research when it came out was kinda like, maybe you guys were already doing it, but to me, was new. It was cool. But maybe completely different domains or, yeah, use cases.
00:37:35 · Thariq Shihipar
[00:37:35] S0: Yeah. Is harness design... Is tricky, I I think. Like, I I think you could probably imagine... Like like, before I came to Anthropic, I I built a spreadsheet agent that was a cogen harness myself, and I do think that that would outperform Claude Code at the specific spreadsheet, like, work. But would it outperform it in a way that's worth it in the sense that the Claude Code harness is getting more on the exponential and I would need to continue to update this harness myself? I I I don't know. You know? So... Yeah. And so your second question, oh, like like crazy things people have done with Claude Code. Yeah. I mean, I... There was a interesting company I saw recently that does it like material discovery. And so basically, what they do is like, you know, you can write code to simulate the properties of a material object and, kind of like, you know, a couple years ago, there was this like LK 99 superconductor thing, that turned out to be fake. But like, what if you could simulate a bunch of these and then figure out like from the simulations, what should I test in the lab and, you know, go test them? So, I thought that was like one of my favorite like, you know, in in new ways to use Claude Code. Yeah.
00:38:51 · S7
[00:38:51] S7: I wanted to get your opinion on the seven x usage gap. So with research saying that power users are getting up to seven times more advanced reasoning capabilities out of frontier models than the average users who are kinda merely using it as a search engine. As a builder, how are you thinking about designing the Claude Code interface in a way to kind of stop that? And can we have a UX design that stops that capability overhang by teaching the users to do more multistep agentic tasks?