AIAI EngineerDec 22, 2025· 9:15

No More Slop – swyx

In this keynote at the AI Engineer Summit, host swyx declares war on slop — low-quality, inauthentic, inaccurate work produced by both humans and AI — arguing that the AI engineering community must elevate taste and accountability. He introduces Swix's law of anti-slop: the taste needed to fight slop scales with the plummeting cost of generating tokens. Swyx demonstrates how to combat slop using AI itself, citing examples like AI News (which tells readers to skip slow days), prompting techniques to avoid slop, and using sub-agents against context rot. He calls for rejecting autonomy without accountability and urges the audience to say "no more slop" to bosses demanding more lines of code, untested releases, and engagement bait.

Transcript

Declaration0:00

swyx0:21

Morning. How's everyone doing? Good? I'm going to need a lot of energy for this talk, so please back me up. I'm very nervous, but we'll get through this. I'm declaring war on slop today. Let's talk about this. Every AIE has a secret.

I've told this to some folks that are personal friends, and I'll just show the secret now. The first summit, we had the secret, which was we knew that the AI engineer was going to be a thing. Second summit, we extended it to leadership.

Third summit, we realized that basically we always needed to concentrate on model labs, and that's why you see all the top-tier labs here today. World's fair, we started expanding the TAM of what AI engineering is affiliated with, with AIPMs and AI designers.

And with the code summit, as Jet just talked about, we really started to focus on curation and focusing in on a theme. And if there's one theme that really matters this year, it's coding. But I'm not here to talk about coding.

The rest of the day you're going to hear about coding. So just indulge me five minutes to talk about slop. We've done really well,right? And I think slop is sort of associated with quantity and quality, and I think that's something that I'm really trying to think about as well.

How do we grow this community, grow this industry, and grow this event with the same kind of taste and high quality that you've come to expect? And this is something that, you know, I hope hopefully you guys can see that we care a lot about in curating all of you coming here and all of the speakers that you're about to see.

We're in a war against slop. This is actually the Oxford English Dictionary. This is a candidate for the 2024 Word of the Year. It lost to Brain Rot. But slop is pretty good, and I think it's probably gone even more of an issue this year than last year.

Defining Slop1:53

swyx2:12

Maybe it will win this year. I have an issue with Oxford, though, because they did us dirty by saying slop is generated using artificial intelligence. The other part I agree with. It's low quality, inauthentic, and inaccurate. But it doesn't take AI to be low quality, inauthentic, or inaccurate.

Any human or AI can be an agent of slop,right? You've seen this yourself. I'm going to indulge me with a few examples. By the way, I got this, if you're not familiar with internet slang, the opposite of slop is keyno.

And I got this idea from Paul Rambles, who, like, you know, when I do Sora videos, I do really boring Sora videos with me and Sam Altman. When other people who are actually creative and good at these things, they do cats playing DJ Drews.

Keyno vs Slop2:44

swyx3:01

Slop can be produced by the same studio. There's K-pop Demon Hunters by Netflix and there's Electric State by Netflix.

Slop can be produced in tons of different models. No comment.

Slop can be something that's keynote can degenerate into slop,right? If you're early on the trend and you're starting that and it's fresh and new, that's great. If you recognize the other image, you're too online.

OK, not enough people recognize that image.

Go do your homework. Yeah, and obviously I'm just going to throw in a dig at Game of Thrones because this is the same thing,right? Like slop is everywhere. It's generated by humans and AI. You get it. OK, the same startup idea can be keynote versus slop.

When I first presented my first keynote at the AI Engineer Summit, we actually used Tome, which is like an AI slides company. I loaded up the same slide deck and it was gone recently because it was actually sort of closed as a company.

There's different takes on vibe coding, and I think one of them is much better than the other. And I think these are just like the tensions that we have to navigate. One of our speakers later on, Xoal Meter, I think it's really interesting that both of them are exponential charts, but one of them feels more keynote and the other is more slop.

And I think I would really like to have people investigate why. So let me just skip through. Basically, we're in an asymmetric war on slop. I think the closest law that I found that matches this is Brandolini's law, which actually states the amount of energy needed to refute bullshit is an order of magnitude bigger than we needed to produce it,right?

Asymmetric War4:22

swyx4:43

So we need to coin an appropriate law as well because

the cost of generating tokens is dropping by 100 to 1,000 times every single year. So this is, I guess, Swix's law of anti-slop. The amount of taste needed to fight slop is an order of magnitude bigger than that needed to produce it,right?

There's so much low taste out there. We need to elevate what's out there in the world because that's what we stand for as humans. I think there's a positive message. You can use AI to fight slop. I'm proud to run a society project, AI News, which is the only newsletter that tells you not to read it when there's nothing going on.

Fighting Slop5:03

swyx5:22

Thank you. Oh, appreciate that. You can also prompt to fight slop. The next speaker is Mahesh and Barry. I found this in the sort of prompts, in the skill set that they put, where they actually acknowledge slop and tell Claude not to produce slop, and it actually improves significantly from left toright.

Code Slop5:43

swyx5:43

What about code slop,right? We hear about code. Creating tech debt where you can sort of two engineers can create a tech debt of 50 engineers. Or on a more serious note, you can start exposing private data of millions of users.

And this all happened this year. Everything I'm mentioning all happened this year. I'm kind of using this keynote as a way of recapping. And just to be spicy a little bit, even people who are saying things like, oh, my model can go up to 30 to 60 hours autonomously, well, it feels a bit sloppy because you're also not saying, well, was the code good or not.

You're just saying how long it went. So in the same way that you have no taxation without representation, you don't want autonomy without accountability.

Something I've been working on more recently is that using AI to fight code slop as well. So this is from the a bunch of people quoted this yesterday, the semi-async value of death, where you can sort of keep human attention and mind-meld with the machine in order to work on the hardest problems, whereas the stuff that's commoditized, you can make it more async.

So you can check out more on that details. What seems to be less appreciated is the other work on code maps, which I more recently done, where we actually use AI to scale code-based understanding, which is also a way to fight slop.

Computer Use6:57

swyx6:57

And you can talk to the cognition folks downstairs who can show you more in detail. The last thing I always want to shout out as well is this trend of computer use. I think computer use kind of debuted this time last year with Anthropic, but it's getting really, really good now, guys.

It can really autonomously operate the most complex apps, including an ID. So I think that's really exciting, and you should probably use that to fight slop. We use it for the website, and here's an example of us using Devin to automate the website updates.

And finally, something I learned from this conference yesterday is that you can also use sub-agents to fight context rot. And I think that is one of the biggest themes that I'm observing as well, if you want to take away something from this conference.

And also, one of the biggest highlights of the year for us as AIE and myself personally was chatting with Greg Brockman, who always preaches the concept of modularity, where you can sort of keep clear boundaries on what is human designed and let the AI code everything in between.

No More Slop8:00

swyx8:00

So these are all ideas, but I just have this one message that I want to compress down to you today that I want you to say with me. No more slop. Yeah?

Your boss tells you, I want more lines of code by the end of the quarter. What do you say to that? Say it with me. No more slop.

You're fighting an asymmetric war. This is how bad it is,right? You have an insufficiently tested release that is potentially embarrassing to your company. What do you say to people who really want to push it? No more slop. Exactly.

Your Twitter algorithm wants engagement bait and is sort of

telling you to lie, basically, to the broad public. What do you say to that? Exactly. That's it. I hope you have a great conference, and let's hear it for not having any more slop. Thank you.

Guest8:57

No more slop.

swyx8:57

Thank you.