Related posts
Sebastian Raschka GitHub
mini-coding-agent — Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.
The subject this post names, from the same vocabulary the directory files beliefs under, and the words it uses that this site has seen least often elsewhere. Posts are matched on those words alone — nothing here is a summary of this one.
Top people
Showing Profile →
Hiding
Hiding
20 September
-
korrents.com
Frontier AI coding agents can now fix complex compiler bugs like LTO issues in about fifteen minutes.Their words
Strap a frontier AI into a good coding harness, show it what's broken, give it all the sources (source.tar), and ~15 minutes later I have a patch.
What's been going on in w64devkit the past yearnullprogram.com
19 September
-
korrents.com
Having the very best AI model and harness does not result in better or faster execution and can slow teams downTheir words
having the very best AI model and harness doesn’t result in better/faster execution - in fact it slows you
18 September
17 September
16 September
13 September
-
korrents.com
Software is mostly dead; new Silicon Valley startups are building harness or hardware instead.Their words
In the most early adopting tech pioneering place that's Silicon Valley new startups aren't even building software anymore And it's debatable if anyone will actually need a custom harness or it won't just be generically offered by the AI frontier companies So software is mostly dead and hardware it is
12 September
-
korrents.com
Codex lets you use any model and has an open-source harness, while Claude Code does not and is closed sourceTheir words
Codex lets you use any model you want (not just OpenAI) and harness is open source - Claude Code doesn’t and is closed source Given this is the two leading AI labs, notable difference in approaches
11 September
-
Their words
what Meta has assembled is free (to consumers) hardware and software that dramatically reduces the barrier to entry for ordinary people looking to harness the power of agents, making the AI upside a lot more accessible to the masses who don't want to buy a Mac Mini.
9 September
-
korrents.com
Computer-use capability will be a major focus of LLM and coding-agent development in the coming months and years.Their words
I expect the upcoming months (or years) also to be an era of computer use refinement on both the LLM and the agent harness layer.
8 September
6 September
-
Their words
to make *actually* good software, you have to use it a lot but many people are spending more time in their coding agents/factories than in the apps they're building - so they won't
5 September
4 September
-
Their words
This kind of thing will be exploited. Think Solar Winds–style supply chain attacks.
3 September
-
Their words
so harness capabilities are increasingly shifting into the model itself.
-
Recommendstheir ownrcmnd.app
Vercel AI GatewayTheir words
Points all coding agents to AI Gateway, getting you 100% uptime, observability, budgets, and ease of switching.
-
Lovedrcmnd.app
GPT-6 AstraTheir words
GPT-6 Astra represents a step-function change in model capability for interactive reasoning problems. It scores 66% on ARC-AGI-3 using our standard harness, and nearly 100% with a continuous conversation harness and custom compaction, at a cost of roughly $360 per game.
2 September
31 August
29 August
26 August
25 August
-
Their words
I’m thinking about banning Claude code at Shopify until they change their mind and read AGENTS.md and .agents/skills etc. Insisting on only reading CLAUDE.md sometimes leads to split brain problems when different team members use different tools. Just unnecessary.
22 August
20 August
19 August
-
korrents.com
Coding agents make every plugin interface you ever blew off trivially usable, which is a large productivity win.Their words
I can't say enough how excellent a coding agent is at customizing Chrome with extensions. A huge productivity win. Every plugin interface you've ever blown off is now trivially usable.
14 August
-
Their words
buuuut my roadmap is’nt ten times shorter. and I’m definitely not ten times better at deciding what is worth building. teams haven’t started casually shipping a year of product work every month. you can look around and and it’s hard to say what software has gotten meaningfully better in the last year.
12 August
10 August
-
Their words
So maybe write this one down. Your dependencies business model is your business model.
8 August
-
Their words
I REALLY want to believe that this fixes prompt injection risks for coding agents, but I'm just not there yet
-
Lovedrcmnd.app
Servus: How Slavery Made the Roman EmpireTheir words
A very good and aggressively readable book about how terrible slavery was in the Roman Empire.
30 July
-
Their words
Um, and to give you an example of a a a use of a coding agent that works extremely well is you can ask today's models to translate software from one computer language to another very effectively because in that case you actually have a incredibly detailed specification.
27 July
-
Their words
I think evals, they outlive the harness a little bit, but not by that much. Like an eval might live for maybe one, two, three model generations, but nowadays the you know, we're on the exponential. The model is improving so quickly, very often we just saturate the eval, and then we have to throw it away, and we have to come up with a new eval.
26 July
-
Their words
we we kind of have coarse level uh recursive self-improvement already. And the fact that every time you use it, it improves the markdown files. Uh every time you use it, it updates its uh long-term memory.
24 July
22 July
-
Their words
I genuinely believe that if you took an open weights model from 2025 and built a pentest harness for it, it could do this kind of sandbox escape and scan/hack in most networks. This is only surprising because you assume OpenAI has sounder sandboxes.
20 July
15 July
From one piece Context engineering with Dex Horthy 2 beliefs, in the piece's order there
-
Their words
But it's basically this idea that like the only thing that made claude code good was reinforcement learning. And the dimension along which it got good was like we made a model. We trained the model and the harness together. And so the model got really good at calling the specific tools in that harness.
-
Their words
Well, harness engineering just is like how do I raise the floor so that every single turn of this thing, the results are as good as possible.
14 July
6 July
-
Their words
I believe the same is true of the current intelligence explosion being driven by AI. We are in desperate need of new social structures that allow us to harness its power, without damaging or destroying human values in the process.
4 July
-
Their words
harness improvement enables better deployment of the model but intelligence is still the core.
Harness Engineering for Self-Improvementlilianweng.github.io
30 June
27 June
From one piece Using Local Coding Agents 2 beliefs, in the piece's order there
-
korrents.com
When an AI lab builds both a model and a coding harness, the model is optimized for that lab's own harness first.Their words
if an LLM developer also develops a coding harness, it is somewhat safe to assume that their model is optimized for their own harness first
-
Their words
untrusted repos should be treated as hostile by default because they can steer the agent toward reading files, running commands, or sending data through approved tools.
15 June
3 June
27 May
From one piece Building OpenCode with Dax Raad 2 beliefs, in the piece's order there
-
Their words
We're now doing it in a much heavier way because we find that these like kind of bory enterprisey uh patterns end up being pretty useful because you have a bunch of idiots on your team now. The coding agents are a bunch of idiots and they are going to work 24/7 and they're going to like ship a lot of stuff. So you need way more guardrails than you used to.
-
Their words
And our harness wasn't very good for like the first like five months of open code. But it was good enough. It was good enough that most people couldn't really tell a difference. And once we won enough share, then we went back and like tried to make our harness like good and smart and optimize and all those things. But uh it was inverted from what everybody else was doing. Everybody else was being like you have to build the smartest harness and that's how you win.
18 May
28 April
7 April
From one piece Should Designers "Code"? 2 beliefs · lukew.com
-
Their words
There's a question that never goes away in design: should designers code? My answer has always been yes. But for a decade or so, the complexity of front-end development made it impractical for most. Thankfully, AI coding agents have reopened the door.
-
Their words
For years, it was faster to mock up software than to ship it. Designers stayed "ahead" of engineering with prototypes. Now AI coding agents make development so much faster that the loop has flipped.
4 April
3 April
-
Their words
the likelihood of inspiring someone to build a competitor was too high, and the return on sharing was too low to justify the exposure. That threshold has effectively collapsed to zero.
The Increasing Risk of Building in Publicthebootstrappedfounder.com
1 April
-
Their words
it required a different way of thinking and the cognitive load might be a little higher but the output is dramatic and we have seen our best engineer double their output.
20 March
-
korrents.com
What limits you with coding agents is your own skill at stringing them together, not the capability of the models.Their words
I think to a large extent you feel like it's a skill issue. It's not that the capability is not there. It's that you just haven't found a way to string it together of what's available.
19 March
From one piece Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summit 3 beliefs, in the piece's order there
-
Their words
the key thing about TDD is that it means that the agents won't write more than they need to.
-
Their words
I think I see people who are writing code with coding agents and they're not writing any tests at all. That's a terrible idea.
-
Their words
I think that might be what saves us. I think the fact that no, you can't have one engineer and have him do a thousand projects because after three hours of that he's going to literally pass out in a corner.
11 March
-
Their words
So I think we're in a weird limbo for the rest of this year okay where until the UIs arrive that are good enough for everybody who can't read everybody who can't read is going to be a severe disadvantage.
2 March
1 March
13 February
-
Their words
But the quality of these systems isn't just in the code they write. It's also in the code I don't have to write. And maybe more importantly, their actual value is in the code I would never have written, or could never have written, or never would have wanted to write.
When Long-Term Investments Finally Pay Offthebootstrappedfounder.com
12 February
-
Their words
It's the same way as you have to play with a guitar before you can make good music. It's, it's not, oh, I, I touch it once and it just flows off. It, it's a, it's a, a skill that you have to learn like any other skill.
-
korrents.com
Being an excellent programmer is a burden rather than an advantage when learning to work with coding agents.Their words
It’s actually how good they are at programming is almost a burden in their ability to empathize with the system that’s starting from scratch. It’s a totally new paradigm of, like, how to program. You really, really have to empathize.
24 January
-
Lovedaffiliate linkrcmnd.app
Wyatt harness bootsTheir words
I've worn my Wyatt harness boots for years and they're still pristine.
19 January
-
Their words
But with today's AI coding agents, building software is remarkably easy. So instead of handing over static assets and static guidelines, designers can deliver custom software. Tools that let clients create their own on-brand assets whenever they need them.
8 January
7 January
-
Recommendsaffiliate linkrcmnd.app
Chatter: The Voice in Our Head, Why It Matters, and How to Harness ItTheir words
can lead to imposter phenomenon. In this book, a leading psychologist looks at the science behind our inner voice and new research into how to harness it and improve your physical and mental health.
3 January
1 January
-
Likedrcmnd.app
Number Go UpTheir words
I didn't read much non-fiction this year, but the best of what I did read was Zeke Faux's Number Go Up about the cryptocurrency bubble. This book will not change anyone's mind, but it's a readable and entertaining summary of some of the more obvious cryptocurrency scams. I also had enough quibbles with it to write an extended review, which is a compliment of sorts.
31 December 2025
-
Their words
I run in YOLO mode all the time, despite being deeply aware of the risks involved. It hasn’t burned me yet... ... and that’s the problem.
26 December 2025
-
Lovedrcmnd.app
A Little History of the WorldTheir words
This was probably my favorite book of the year. Gombrich wrote it in six weeks at age 26, aiming to explain world history to children. The result is remarkably readable.
22 December 2025
-
Their words
A very good and readable book on this interaction, with excellent discussions of Donna Summer, Stevie Wonder, La Monte Young, and Penderecki, among many others.
21 December 2025
-
Recommendsrcmnd.app
Our Dollar, Your ProblemTheir words
This book manages to pull all of that together in a way that's genuinely readable and engaging, helped along by anecdotes from his own policymaking experience that both clarify the arguments and make them feel concrete and accessible to a much broader audience.
23 November 2025
11 November 2025
-
Lovedrcmnd.app
Letters From an Imaginary CountryTheir words
Theodora Goss's latest book of short stories is 'Letters From an Imaginary Country,' and it manages to be one of the most voraciously, delightfully readable books I've ever read and it's one of the most writerly books, too. What a treat!
17 October 2025
-
Their words
And I kind of feel like the industry it's it's um it's over it's it's making too big of a jump and it's trying to pretend like this is amazing and it's not. It's slop and I think they're not coming to terms with it and maybe they're trying to fund raise or something like that.
14 October 2025
11 September 2025
15 August 2025
25 June 2025
30 April 2025
-
Likedrcmnd.app
The Iliad: A New TranslationTheir words
It's very readable, and captures a sense of what is, fundamentally, a very alien, and often ugly, story in a very alien, and often ugly, world, related in magnificent language.
6 January 2025
-
Their words
So I foresee a world with far more specialized code, with fewer generalized packages, and more readable tests.
30 September 2024
-
korrents.com
Maya hieroglyphs must have been readable across several spoken languages, the way Chinese characters or Latin were.Their words
There must have been a way that multiple languages understood the same writing system. Or maybe there was something like Latin. You know how there was a period in Europe where most people were illiterate and there was this priesthood who all understood Latin and they wrote in Latin? Maybe the hieroglyphs represent a kind of Latin in the ancient Maya world.
25 August 2024
-
korrents.com
Almost every one-to-one Telegram chat, and every group chat, is readable on Telegram’s own servers.Their words
The practical impact is that the vast majority of one-on-one Telegram conversations — and literally every single group chat — are probably visible on Telegram’s servers, which can see and record the content of all messages sent between users.
Is Telegram really an encrypted messaging app?blog.cryptographyengineering.com
31 March 2023
-
Likedaffiliate linkrcmnd.app
Alberuni's India: An Account of the Religion, Philosophy, Literature, Geography, Chronology, Astronomy, Customs, Laws and Astrology of India about A.D. 1030Their words
It's mostly readable, though there are quite a few places where the translator calls for more research and this reprint, naturally, doesn't say whether it's been followed up *. In any event, I found this fascinating.
17 January 2023
-
Likedrcmnd.app
The Linux Programming InterfaceTheir words
The Linux Programming Interface by Michael Kerrisk – an exhaustive reference on how Linux works. There are about a million chapters, but every individual chapter is pretty short and I find it quite readable.
10 December 2022
-
Lovedrcmnd.app
Streets of Gold: America's Untold Story of Immigrant SuccessTheir words
Absolutely. It is incredibly enjoyable and readable. The authors, in a way that is very rare for economists, find small stories that paint big pictures for the points they make.
2 March 2022
From one piece Write plain text files 2 beliefs, in the piece's order there
-
Their words
That's why I only use plain text files. They are the most reliable, flexible, and long-lasting option.
-
korrents.com
Plain text is the only format guaranteed to be readable on devices that do not exist yet.Their words
Every device, including ones long gone, and ones not invented yet, can read and edit plain text.
8 December 2021
Nothing matches.
What is a korrent?
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.