Alan: Look at that. Look at that sauce. Fully incorporated. I'm sure the model labs love that. That's the answer. This is getting chaotic, dude. This is fun. Hey guys, welcome to In Context Cooking, a show where we take one dish, taste it, and try to recreate it with minimal help. My name's Alan, and today we have a very special guest, the man behind context engineering, Dex Hory, founder and CEO of Human Layer. Welcome, Dex.

Dex Horthy: Dude, I'm so stoked to be here.

Alan: Yeah, I mean I always start off with this. So on a scale of 1 to 10, how would you rate yourself as a cook? One being bad, 10 being amazing.

Dex Horthy: I would put myself at like a seven or eight. I don't cook that much anymore. And I do it because it's kind of like fun. I the idea of just following a process which is very deterministic uh but also kind of chaotic is is uh is a lot of fun.

Alan: yeah, we like that chaotic but with um certainty. Looking at these ingredients we have before us, do you have any guesses of the dish we're going to try and make?

Dex Horthy: I mean, clearly we're doing some sort of noodle. I see some bok choy. Um, I'm But yeah, I I I don't know a lot about noodle dishes, so I'm excited to see what we got.

Alan: Yeah. So, the dish we'll be trying today is dandan noodles.

Dex Horthy: Oh, nice. I love dandon noodles.

Alan: Okay, great. Because we do have some chili oil here. I've read that you've started coding since you're 17 and you had an internship at NASA for the Jet Propulsion Lab. Yeah. So, like how does a high school kid end up getting an internship at this very prestigious lab?

Dex Horthy: Uh, so they do have they had this high school internship program where it was like they would take for a summer it was like summer after my junior year. Yeah. And they just like put us up in dorms at a local like university that was kind of empty. And so there's the reason why people want to go explore the south pole of the moon is because there's like craters there that are so deep that there is like frozen ice there. The moon's very dry, but in these craters there's there's uh water that has never been hit by sunlight...

Dex Horthy: And so it's like oh we really want to go see what's in that ice and collect samples and study it. problem is very very deep craters and so like most of the rovers can't do it and so we had to like we were basically like building some like pathf finding algorithms... I was 17 I didn't have a CS degree like so we built a very naive implementation of Dystra's algorithm to like find the shortest path according to some like constraints of what the rover could do.

Alan: great yeah I mean that's a great start... How did you get into context engineering? I feel like, you know, coining the term... According to Swix, there are there are many people who who uh Gemini thinks it was Andre Karpathy.

Dex Horthy: Okay. I mean, that's a very valid guess. yeah. So, basically I was building like dev tools for AI engineers. Okay. And uh what happened was I like talked to all the best founders and engineers and founding engineers that would like take my call and I was like, "Hey, we're making this thing that helps you build better agents."

Dex Horthy: And the problem was was that when I talked to all these people who were shipping like real AI to the enterprise like reliable systems... it was like an old tweet from uh from like Swix actually was this idea of like the way the top 1% build is so different from the bottom 99%. You have all your like indie hackers and like open source frameworks that are very very popular... and then you go see how real people are building stuff and getting reliability and it's completely different.

Alan: why do you think there's such a discrepancy?

Dex Horthy: I think there's a difference between like people who want to build like reliable software and people who want to build a cool demo. I think that's the incentives are different. The incentives of like okay if this is right 80% of the time that's fine. It'll look good on the demo... but if you want to go sell something to a real company... it's got to be much more uh bulletproof. So, I learned all this stuff and I was like, damn... So, I wrote down everything that I learned and I called it among other like there was 12 chapters. There was only one of them was really about context engineering.

Alan: Yeah. Cuz you had a couple AI engineering talks that um even recently right in New York. No vibes allowed was it the title that you know had had some good reception. One thing that was very commonly said even I think Swix had a talk about it was about slop and I'm kind of slop. How do you define slop?

Dex Horthy: I mean it's kind of fun. The word has kind of evolved... I think of just like any like loweffort or like contrived or derivative thing that is like someone didn't put a lot of effort into. Yeah, it's obviously most common when someone just like uses AI to write a 10page document that they didn't read and is like full of garbage.

Alan: How have you seen the craft of context engineering change over the past, I guess, year? We had much smaller context uh windows uh but then now we have a lot larger ones and so probably the needs change.

Dex Horthy: Well, so I think there's two competing things here, right? There's this idea of like as the models get better, you don't have to do as much context engineering to get the same quality of results... but I know a bunch of engineers who got really good at context engineering and they were getting the same results from Opus 4.0 and Opus 4.1.

Dex Horthy: It's like Opus 4.5 is AGI uh for people who didn't want to put in the time to learn how to do it... there will always be a thing that the model can like only kind of get right reliably. Like you find a thing that's right on the boundary of the model's capabilities and you figure out how to get it right over and over and over again.

Alan: You mentioned I think in the most recent AI engineering talk about what was it the dead zone where it's like the dumb zone.

Dex Horthy: You got the dumb zone right here... the idea with the dumb zone is also like it's kind of meant to be a rule of thumb... training wheels is like when you get to 40% start thinking about wrapping it up or like like doing a like you know intentional steered compaction to where you want to be... if you don't know and you haven't developed the intuition, then like I tell people like shoot for 40% if you're learning.

Alan: Gotcha. And so like how does someone even like get familiar and build this intuition?

Dex Horthy: uh yeah talk to cloud for 70 hours a week. [laughter]... just use AI as much as possible. Make mistake... we developed this framework called like research plan implement... the only way to know how much context engineering to use on a given problem, I think, is um you just have to get some reps.

Alan: do you have predictions going into like 26 27 even the next you know couple years about how this industry will change that are top of mind?

Dex Horthy: I don't believe the like software engineering is dead and there will be more no more no more coders. I think the the way I would describe it is like the role of the software engineer will change from like write working code to like produce working code or like cause working code to be produced.

Dex Horthy: And one of my biggest pet peeves is the people who run around Twitter talking about how much like cloud code they spent and how many tokens they did... stop we need to talk less about how much like code we produce... there's a difference between coding and shipping. Coding is like making the software work... Shipping is like getting it into prod fixing the things that are broken maintaining it over time... our company is called human layer because we used to do human in the loop but now it's a little bit more like I think about it as like what is the high lever things for humans to do and like what is the things that we can like leverage AI for.

Alan: Okay. I'm in the assembling stage right now... Yeah, but no rush, of course.

Dex Horthy: My plating is not going to look as good as yours, but we're going to figure it out. Yeah, taste is all that matters. This is why I love cooking for myself, because I like I don't want to have to care what it looks like. I'll eat I'll eat the ugliest slop in the world if it's delicious.

Alan: Let's give it a try. Let's give it a taste... Cheers.

Dex Horthy: I really like the like something about this one is like it's more well-rounded. It just like the flavors all come together in a nice way.

Alan: So, I give Dex the slight win here. They all use the same ingredients... but I just like the texture and the flavor. And also, I really like the the extra protein.

Dex Horthy: I took a bunch of noodles out. I was like, I want I want more pork. I want the ratio... I'm on Twitter, Dexorthy... and then we are we just rebuilt our product from scratch. It's an agentic IDE. It's uh coming out soon and uh you can go sign up at human layer.dev.