Latent Space: The AI Engineer Podcast
00:13:13 · Mihail Eric, Shawn Wang, S2
In that way, there's effectively this, like, passing on of, like, the guard of true good software design in a way that, you know, I don't think most students get the opportunity to do. And then there's the benefit, of course, that, like, I'm sure some of them will get, you know, poached and picked up as part of doing well in those assignments. [00:13:28] S0: Yeah. One of the interesting things, you know, for what it's worth, I'm I'm gonna get a bunch of hate if I don't say this. I think you say cooked and versus cracked for dramatic effect. But, you know, like, it's just nice to to state extremes. Sure. Sure. Yeah. And so so maybe we should go into the sort of detail of the curriculum, or is there anything else you wanna explore at the top level? [00:13:48] S1: I mean like that, that's a very helpful. Yeah. All that's there. [00:13:52] S2: I have high level questions about students using tools, best practices. Are you pro it like individual tutors? I'm assuming this will also be picked up by students. So, before we dive straight into the course, just anything you have guidance on there for? [00:14:11] S1: Like in terms of what... [00:14:11] S2: Yeah, you said you're passionate about education, right? Like there's also a stigma of one side is how do teachers, professors use it? And then how can students best use these tools? That's not just throw your assignments in, it can kind of one shot it. How do you still learn? Like if you have anything there?
00:14:11 · S2, Mihail Eric, Shawn Wang
[00:14:11] S2: Yeah, you said you're passionate about education, right? Like there's also a stigma of one side is how do teachers, professors use it? And then how can students best use these tools? That's not just throw your assignments in, it can kind of one shot it. How do you still learn? Like if you have anything there? [00:14:28] S1: Yeah. Yeah. And I think that there's... I still have some assignments thrown in there, which I think are not intended to be the hardest things in the world, but are meant to be more about, like, concepts, like, more conceptual things. Like, you know, what does a skill mean? Sort of like the... Maybe more of the the the tactical of some of these tools, skills, like, you know, agent ready code bases, like agents MDs, things like this. So there's a a certain amount of just, hey, if you haven't heard these terms, kinda get up to speed on them. I do think most of the learning, in terms of the kind of putting the tools to the test, will happen both in the OSS and then also in the final project, where it's very open ended, and they'll have to just kind of explore something interesting. [00:15:03] S2: Cool. [00:15:04] S0: Yeah. Maybe... I just want to talk about, well, let's go through one, two, three, four, to 10, and then we'll dive in deeper. So like breadth first, basically. [00:15:13] S1: Sure, sure. Yeah. So we start with [00:15:16] S0: the internals and coding agents. You teach people how to write their own clone. It's very helpful that it's not open source. And then?
00:15:24 · Mihail Eric
[00:15:24] S1: Yeah, yeah. So week one, it's all internals of harnesses, kind of build a coding agent from scratch. Week two is more, okay, now assume that there's... How do we start thinking about context engineering at scale, so beyond just vanilla prompting? And then I think coupled with that is just, in in doing that, thinking about tool design, MCP, you know, people... I think for a while, MCP was getting a of hate. I'm still pro MCP. I see it all the time. And so I think that there's... At this point, it's a standard that's existed, and I think it will continue to exist. So, you know, talking about that, effective tool design, that's week two. Week three, I would say, is more about just like skills and what does it mean to extend beyond simple, single purpose tools to more like procedures, and that's where we'll talk about skills. That kind of starts leading into, like, the automation of agents. Before is is a lot of just more of, like, the foundational pieces of how can you customize an agent. This is things like agent config files, a la AgentsMD, CLAUDE.md, hooks, you know, kind of sub agents. Like, there's a lot of mechanisms that exist in modern harnesses, which you can use for different purposes. So I wanna expose students to that. Agent ready code bases. This is probably one of my favorite topics. It's like and this is especially relevant for folks that are going into industry and thinking about code at scale is, you know, essentially, what does it mean to have a repo that's ready to be ingested, consumed effectively by an agent? And so thinking a lot about, you know, the trade offs of designing of kind of service level boundaries, but also docs and and verifiability and things of that nature. So that's week five. Yeah. Week six, sort of genetic code review. And here, I think what is interesting is thinking also kind of extending from week five week five around code base, like agent ready code bases. Going to week six is more about, like, okay. In order to... Like, code review is now becoming a bottleneck, which I don't know that students, unless they've, you know, have done a lot of... Some of them are master's students, they've been in the industry, but a lot of them have not seen this. But for most people that are using CodeAgents today, we're all experiencing something of a new bottleneck in CodeRevu.
00:17:26 · Mihail Eric
So how do we unblock that or unbottle the the bottleneck a little bit? What mechanisms are there there? And so verifiability and, you know, things of that nature and how we can extend that into the code review process. Week seven, security. I mean, obviously, I think there was a point... So this was in last year's class as well, and this this I wanted to reinforce. I mean, with any autonomous system taking a lot of actions, we're seeing a lot of... This year, especially, a lot of things getting hacked, you know, and not least of which are are just some of the the core pieces of software from from Vercel to, you know, gateways, LM gateways entirely. So I wanna spend some time just, like, talking about what new attack vectors exist exist in security and and, you know, how we can mitigate some of them. Week eight is background agents. So this is, what I wanna start touching on here is, you know, how do you, like, basically run agents in many different, like, product service areas, not just in what was traditionally an IDE, but also having things that are, like, based on triggers in your code base, in in your repo, you know, during CICD, things that get triggered even when, you know, based on events, things like SRE style bots. How do you even build a system like a... I think this past year was when a lot of companies started releasing their posts like Ramp Inspect. There was... Spotify has their own version of this. You know, I think Stripe Minions, so all these folks were doing really cool write ups of, like, their internal info they were building to do this. I wanna touch on that, get people exposed to what that is. Yeah. This is, yeah, this one is more on, like, what happens when you're in a team in in the modern world and sort of, like, the core pieces of of team level infrastructure. So everything from, LM gateways to, you know, MCP portals, which is, like, MCP at scale. And then just also how to think about the evolving roles, I would say. So this is maybe a little bit like a soft thing. It's like, what is now... And the vanilla, maybe not super nuanced thing to say is like, everyone's a builder, but I wanna go a little bit deeper beyond that and sort of like, what thing is actually getting subsumed? What roles are actually either evolving or merging that didn't once exist?
00:19:28 · Mihail Eric, Shawn Wang
What should students think about in terms of defensible skill set that maybe wasn't true before? And so a lot more team dynamic type considerations. And then, yeah, this is a... It all kind of builds up toward the toward the factory, which I think is top of mind for now, for a lot of folks today. Whence we're we're building factories, where do humans still exist and all that? What is the... You know, where are the new choke points that that are intentionally there around around human involvement? Things like intent, things like setting up a verifiable systems, and what happens in the limit when maybe 89% of code is fully driven by just agents, where we kind of filled into all that. So, yeah. [00:20:04] S0: Nice solid 10. I was gonna say, like, you know, some of these are more established patterns than others. And I think people need to know that not all of this is settled science. [00:20:18] S1: True. [00:20:18] S0: You know, but it is everything... I'll endorse everything as things that people talk about and you should know. You just... We know the open problems, we may not know the answers.
00:20:18 · Shawn Wang, Mihail Eric
[00:20:18] S0: You know, but it is everything... I'll endorse everything as things that people talk about and you should know. You just... We know the open problems, we may not know the answers. [00:20:27] S1: That's absolutely right. Yeah. Yeah. I mean, even... I mean, you probably have your own version of this. I'd be curious to hear what you think is still defensible, or not defensible, but not as set in stone. But, you know, even like the the softer factory. Are we talking about, like, dark factories? Are we talking about, like, these sort of half lights on factories? Like, I think even there's a spectrum there. Yeah. And there, you know, there's the people that are on the on the very frontier, like like the warps and the factories that are that are, like, building factories and selling them the services. And, you know, even they will only claim, like, 30 some percent, if even that, of of, like, fully, you know, identically driven contributions. So Yeah. What does that mean in the limit? It's... It is hard to say. [00:21:01] S0: And there's people who went very, very far at Dog Factory and then came out saying, was wrong, guys. So we covered that on AIE. Just be aware that not everyone... They probably believe the things they're saying at the time, but they have the right to change their mind, and they do. And even Boris recently tweeted that, like, yeah, I am often wrong. Yeah. Like... And, like, everyone is, like... Because he created a clock code, it's, treating his word as gospel. Totally. And then, no. Well, sometimes he disagrees himself.