Skills are now a valuable form of software, like Emil's world-class design eng work. Projects like 𝚙𝚐𝚋𝚘𝚝, 𝚔𝚗𝚒𝚙, 𝚞𝚗𝚕𝚒𝚐𝚑𝚝𝚑𝚘𝚞𝚜𝚎 create amazing AI engineering loops.
But, simply just having your loops build everything without having some guardrails around the blast radius without having guardrails around how you think about quality, I think is a recipe for disaster.
So if you design call it loop, call it graph, call it workflow, it's kind of all the same. If you design something that gets a trigger or gets an input and does something for you and maybe there's a decision in the way, boom, there's your graph.
And I think there's a lot of room in a lot of domains for much faster validation models, possibly learned valu validation models that can uh you know get you a a approximation to the true answer much much more rapidly. And that changes how those experimental loops can be thought of and how quickly you can go around those loops.
But this is the book that I give to every junior engineer because I think like nobody ever really talks about debugging as like a discipline outside of like basic heuristics.
I still see a craft excellence that's really important in the disciplines that I don't think is going away anytime soon. Even if there's fluidity or blurring of the work across the functional lines.
if you want to do loops engineering, you should build one loop at a time and you should keep them small and contained. Basically, I think everything except stop reading the code is really good advice.
You'll notice what I said was not use loops to ship the features that users want. We use loops to actually improve the codebase quality and we read all the code because we care about how it's architected and we care not just about the system architecture but what I would call the program design
So I think the the thing I'm most excited is actually like what we call like iterated loops or like slow loops where we basically have a cron job. We have the loop the the the structure of the loop is really easy. It's like run this llinter fix one thing commit and push and then we run that every night in our GitHub actions and we wake up every morning to one PR that makes the codebase a little bit better.
I think a lot of the things that people might say that like oh, it was a waste of time to learn this subject cuz I didn't actually use like those details on the job. I think that's a very wrong way to think about it. And I think that's what a lot of people are doing now with AI. Like hey, what what if I'm not going to be writing for a loops a couple years from now. Um I don't think those things are a waste of time.
we went from infrastructure is code to infrastructure is data and infrastructure is code is like if this do that um bring in this module for loops all this stuff and Kubernetes is like no no no you have to specify exactly the containers you want how much memory that they need and then we have the status field to tell you if they were running or not
I kind of went from 80/20 of like, you know, uh to like 20/80 of writing code by myself versus just delegating to agents. And I don't even think it's 20/80 by now. I think it's a lot more than that. I don't think I've typed like a line of code probably since December basically.
Because if it's not fun, if it's not engaging or interesting, if it doesn't feel good, you're not going to stick with it when it gets tough. I mean, this is probably one of the great lessons for life, which is if you're having fun, then then you're dangerous, right? Then you're hard to compete with. You don't want to you don't want to go up against the person who's having a good time doing it because if it feels like a hassle or a chore, that's the person who gives up when it gets difficult.
I think the main muscle you can exercise is this muscle, the muscle of self-discipline. Not your biceps or your pecs or anything else. Because if you get to train that one, everything else just comes by itself.
We live in a culture that preaches self‑esteem more than self‑knowledge. That leaves people morally flabby-performing virtue while outsourcing the actual discipline that keeps ordinary humans from doing monstrous things.
My model is that research requires a mix of skills. The day-to-day coding and execution is crucial. But there's also a set of harder-to-learn conceptual skills, collectively called research taste. These skills take a long time to gain because they have poor feedback loops, but they take very little time to use.
until there are feedback loops of open source AI, it seems like mostly an ideological mission. People like Mark Zuckerberg, which is like America needs this and I agree with him, but in the time where the motivation ideologically is high, we need to capitalize and build this ecosystem around, what benefits do you get from seeing the language model data?
We ought to be especially careful in the cases where what we delegate to a device, app, agent, or system is an aspect of how we express care, cultivate skill, relate to one another, make moral judgments, or assume responsibility for our actions in the world
tech barons are ordinary mediocrities, no better and no worse than the monopolists that preceded them, and any differences come down to affordances in technology and regulation, not an especial wicked brilliance.
Being on call should not be a constant cycle of things breaking down and firefighting, or alerts going off at all hours. This is not ‘normal.’ These are telltale signs of a fragile system and lack of alert discipline.
a lot of industries over time end up not like that. They end up not being actually a fair and free market with market discipline. They end up as something else. In the business world, what they end up with is either just, you know, one company with a full up monopoly or more commonly they end up with what's called an oligopoly
I am going to contend that the primary purpose of the discipline of history is to foster greater historical knowledge in the public, in order that the public can use that knowledge (and the skills that come with it) to make better decisions.
I appreciate this book for its irreverence, the elegance of its prose and because the essays in it are succinct, punchy, with the tyrannical discipline that newspaper journalism has to have.
A korrent is a belief a person has stated in their own words: one
sentence stating the claim, backed by a quote and a source, kept at
korrents.com.
Under a name here, the quoted block is what they actually said.
The korrent beneath it is the claim those words support, in
korrents' wording — tap it to see the record, its source, and who
else holds it.
Nobody here wrote their own korrents. They are compiled from public
statements, and a person can change their mind, which is recorded too.
About the English under a post
Some people here publish in a language other than English. Where they
do, this site shows a machine translation beneath the post, in
this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the
serif above is exactly what the person published, and it is what to
quote them on. A translation can be wrong in ways that matter,
especially about tone.
Only the post's own words are translated. A quoted post, a linked
article and a belief on korrents.com
are left in their original language.