Related posts
Arvid Kahl
x.com
When AI codes and documents for AI.
codes documents
The 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.
Sources
All Writing GitHub x.com Newsletter Recommends Korrents Mastodon Bluesky Blog
Top people
Andrej Karpathy
Karri Saarinen
Boris Cherny
Varun Raj Manoharan
Dan Shipper
Eric Ries
Marc Littlemore
Kent C. Dodds
Steven Johnson
Jakob Nielsen
John MacFarlane
Jon Seager
Showing Profile →
Show everything
Hiding Show them again
Show them again
Further back ↓
Hiding Show them again
19 September
Software engineer and educator; creator of Testing Library and of the EpicWeb.dev and EpicReact.dev courses.
17 September
Non-fiction writer, podcaster and occasional TV host. Author of thirteen books including The Ghost Map, Where Good Ideas Come From and Extra Life, host of the PBS series How We Got To Now, and author of the Adjacent Possible newsletter on innovation.
The camera feature in the @Gemini_Notebook mobile app is so transformative for on-the-go research. I was up in the Sierras working on a new project, and I just took photos of everything, like this museum display. Then I asked for a detailed report of all the info in the image. The text below is what I got back. (I fact-checked it myself and it was 99% accurate -- and some of the text it transcribed is so blurry in the image that it was hard for me to read it.) Next step is to generate documents like this for all the photos I took, and then ask Notebook to highlight all the information that ad… Google Related
14 September
Co-founder and CEO of Linear; previously principal designer at Airbnb, where he led the Design Language System, and founding designer at Coinbase.
With this update we prioritized product management use cases: @linear Loops can now respond to project, initiative, cycle, and issue changes, update Linear documents, and share tailored Slack updates automatically. Quoting @linear New capabilities for Linear Loops: • Trigger from project, initiative, cycle, and issue changes • Edit documents automatically • Send tailored Slack updates 🔗: Related
Usability pioneer; co-founder of Nielsen Norman Group and founder of UX Tigers; author of the ten usability heuristics and of Jakob's Law.
11 September
Creator of Claude Code at Anthropic.
The latest Threat Intelligence report is an absolutely terrifying and important read. As models become more intelligent, without the right safeguards and monitoring they also become more dangerous. Many capabilities are dual use: a model that codes well can be used to hack critical infrastructure; a model that assists with biology research can also be used to engineer the next pandemic. These issues are complex, thorny, and increasingly important for everyone to understand so that the world can weigh in and respond to rapidly escalating risks. anthropic.com
Related
6 September
Co-founder and CEO of Linear; previously principal designer at Airbnb, where he led the Design Language System, and founding designer at Coinbase.
Agents 🤝 @linear Linear documents are just documents meant for writing down things. Projects, issues, views and other entities have different types. I think the structure makes it easier for both agents and humans alike to use the right one. Quoting @faruk_parhat Our coding agents did something interesting… We are both a @NotionHQ and @linear shop, but over time our coding agents seem to have preferred writing docs in Linear over Notion (since they were already creating tickets). And this kind of natural bias and proclivity of coding agents toward Linear sl… Related
5 September
Philosophy professor at UC Berkeley and creator of pandoc, the universal document converter, and of the CommonMark markdown specification.
27 August
Software engineer and engineering leader at Canonical, working on Ubuntu; writes about his homelab, Nix and tooling at jnsgr.uk.
Their words
One of my favourite things about the Yubikey is their ability to store TOTP codes.
Show the whole quote
jnsgr.uk
21 August
Co-founder and CEO of Linear; previously principal designer at Airbnb, where he led the Design Language System, and founding designer at Coinbase.
What improvements would you like to see in @linear documents and team docs? Related
17 August
Senior space editor at Ars Technica; wrote Liftoff and Reentry on SpaceX, and reports on launch and rocket programmes.
Their words
In financial documents, it’s clear that SpaceX views commercial launch as a rounding error compared to revenues from its own satellites in space.
Show the whole quote
arstechnica.com
10 August
Writer on the intersection of technology and finance. Author of the Bits about Money newsletter and host of the Complex Systems podcast; previously at Stripe.
One of my accountants, in response to me hitting them with the usual packet of documents, sent back a very obviously LLM drafted list of 10 questions. First thought: What am I paying you for. Second thought: Actually no, my LLM digests your LLM's output into the context window. LLMs Related
6 August
Statistician and Chief Scientist at Posit (RStudio). Author of the ggplot2, dplyr and tidyverse R packages and of books on R programming and data science.
23 July
Professor at Wharton studying how people actually use AI, and author of Co-Intelligence. Writes One Useful Thing, where the claims are dated and testable because the thing they describe keeps changing under them.
Their words
Copilot, which uses a mix of AI models and is okay for working with office documents but lags badly in terms of its agentic abilities.
Show the whole quote
oneusefulthing.org
19 July
Web infrastructure engineer and standards editor; chaired the IETF HTTP working group and co-authored core HTTP and Atom specifications.
15 July
Founder of HumanLayer; wrote 12-Factor Agents, on how to build AI agents that hold up in production.
16 June
Historian of the Renaissance at the University of Chicago and a science-fiction novelist; wrote Terra Ignota and Inventing the Renaissance.
Their words
And then you look at the actual trial records, and maybe one in a hundred convictions for that crime actually ends in a capital sentence. And almost all of the other ones end in a fine or a public flogging, but not in the sentence that's on the books.
Show the whole quote
youtube.com
15 June
Indian software engineer and co-founder of Skcript; builds web apps and writes at varunraj.in.
4 June
Behavioural economist at Chicago Booth, professor of behavioural science and economics and director of AGI economics at Google DeepMind.
Their words
the ballerina and the kind of performer, that's the wrong reference class. Right now we have a lot of jobs where you have different tasks. So this is the task-based model jobs where you have like a lot of different tasks. So like a doctor, what is their job? They're filling out insurance documents. They're you know, going and like calling different pharmaceutical companies. And one of their tasks is to actually see the patient and talk to them, but that's like actually not the main part part of the job.
Show the whole quote
youtube.com
24 May
Co-founder and CEO of Every. Writes the Chain of Thought column about working with AI tools and hosts the podcast AI & I.
From one piece
AI predictions: Job markets, Codex beats Claude, and the death of org charts | Dan Shipper
2 beliefs, in the piece's order there
Anthropic
Their words
The second is that most of the work that you do is actually going to happen on your computer in an environment like Codex or Cloud Co-work that becomes the sort of operating system for it becomes the sort of operating system for how how you do all of your work, whether that's your email, the documents you create, like all that kind of stuff.
Show the whole quote
youtube.com
Their words
I think that we will be reading way more AI generated writing in documents and emails and we will like it.
Show the whole quote
youtube.com
10 May
Author of The Lean Startup and Incorruptible, and founder of the Long-Term Stock Exchange, who advises companies on corporate governance and mission protection.
From one piece
How Anthropic, Costco, and Patagonia all build incorruptible companies | Eric Ries
2 beliefs, in the piece's order there
Their words
did you know that according to the legal documents you yourself signed, your company's literal charter that you have right now, and this is not some hypothetical future thing, you've already put in motion, a rule that says you have a fiduciary duty to say yes in this situation.
Show the whole quote
youtube.com
startups
Their words
According to Harvard Law School, among venturebacked companies that have the standard best practices set up that you got from your lawyer, okay, only 20% of founders are still the CEO 3 years after going public.
Show the whole quote
youtube.com
23 April
Software developer and entrepreneur; co-founder of Heroku, author of The Twelve-Factor App, and a researcher at Ink & Switch.
It's astonishing how much time in my day I spend typing in two-factor codes, picking the right Google account, and otherwise trying to convince the computer that I am who I say I am. I believe we can do better. Would love to see a talk submission if you're working on this. Quoting @localfirstconf "It's been a kind of a good deal to say like, look, I'll just let Google manage my identity and then I can click the login with Google button everywhere. But it's a little bit of a deal with the devil. " @_adamwiggins_ Google Related
12 April
Sociologist at Duke University writing on markets, exchange and moral order, and on plain-text and data-visualisation tools for social science.
10 April
Ruby and Rails core committer known online as "tenderlove"; maintains Nokogiri and works on Ruby performance.
2 April
Founding member of OpenAI and former director of AI at Tesla; creator of nanoGPT and the term "vibe coding".
LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki… LLMs Related
20 March
Founding member of OpenAI and former director of AI at Tesla; creator of nanoGPT and the term "vibe coding".
documentation
Their words
It used to be that you have documentation for other people who are going to use your library, but like you shouldn't do that anymore. Like you should have instead of HTML documents for humans, you have markdown documents for agents.
Show the whole quote
youtube.com
4 March
Creator of Claude Code at Anthropic.
18 December 2025
Founding member of OpenAI and former director of AI at Tesla; creator of nanoGPT and the term "vibe coding".
Their words
Use apps like BobbyApproved and Ivy to scan the bar codes and get a lot of information about all ingredients and a score (I like and use both).
Show the whole quote
karpathy.bearblog.dev
Their words
Use apps like BobbyApproved and Ivy to scan the bar codes and get a lot of information about all ingredients and a score (I like and use both).
Show the whole quote
karpathy.bearblog.dev
12 December 2025
British senior engineering manager at Netlify, previously a team lead at the BBC; writes about JavaScript testing, chatbots and serverless at marclittlemore.com.
Mastodon Been trying to use https://conductor.build/ to run some Claude Code agents in the background while I write some documents. Seems pretty great so far and has a really nice UI/UX for creating PRs. Anthropic Related
Bluesky Been trying to use https://conductor.build/ to run some Claude Code agents in the background while I write some documents. Seems pretty great so far and has a really nice UI/UX for creating PRs. Anthropic Related
25 November 2025
Medieval historian at the LSE; writes Going Medieval and The Middle Ages: A Graphic History, and spends a lot of it correcting what people think the period was like.
23 November 2025
China economy researcher based in Beijing who writes on his personal blog about Chinese political economy, history, books and music.
15 October 2025
Cryptographer; teaches cryptography at Johns Hopkins and writes A Few Thoughts on Cryptographic Engineering.
Two great bits of academic attack work this week. The new one allows Android apps to see data displayed on the screen by other apps, including Google Authenticator codes. pixnapping.com
Google Related
19 September 2025
German writer and historian; wrote Blitzed, on drug use in Nazi Germany, and Tripped.
Their words
So the Navy hired the shoe runners unit from the SS, paid them money, and then gave them drugs, different kinds of drug combinations, methamphetamine combined with cocaine and chewing gum and all kinds of things. So this is a big thing, you know. And there are documents to it.
Show the whole quote
youtube.com
29 August 2025
Economist specialising in global income inequality; formerly lead economist in the World Bank research department, now at the CUNY Graduate Center and author of the Global Inequality and More newsletter.
Their words
As Quinn Slobodian documents in his excellent book Globalists: The End of Empire and the Birth of Neoliberalism
Show the whole quote
branko2f7.substack.com
9 April 2025
Member of technical staff at Anthropic. He has led ML/AI teams at Amazon, Alibaba and Lazada, and writes about LLMs, recommender systems and engineering at eugeneyan.com.
If you were building a Q&A feature (or chatbot) based on very long documents (like books), what evals would you focus on? Related
26 March 2025
Indian software engineer and co-founder of Skcript; builds web apps and writes at varunraj.in.
Their words
My everyday office gear that helps me debug, code, write documents seamlessly.
Show the whole quote
varunraj.in
25 March 2025
Co-founder of Sundial; former vice president of product design at Facebook; author of The Making of a Manager; writes The Looking Glass.
7 March 2025
Writes jvns.ca, turning "hard and scary" topics — networking, debugging, Linux internals — into plain explanations and hand-drawn comics. Publishes Wizard Zines, illustrated programming zines. Software developer based in Montreal.
3 July 2024
Software engineer who writes the blog Made of Bugs about performance, debugging and understanding computer systems. Previously worked at Anthropic on interpretability, at Stripe on Sorbet, and at Ksplice.
15 April 2024
Research scientist at Meta in Berlin working on multilingual models and evaluation; led the multilingual team at Cohere and was a research scientist at Google DeepMind before that.
LLMs
Their words
Retrieval-augmented generation (RAG; Lewis et al., 2020), which conditions on the LLM's generation on retrieved documents is the most practical paradigm IMO.
Show the whole quote
Command R+ ruder.io
4 March 2024
Historian of Ukraine at Harvard; wrote The Gates of Europe, Chernobyl and The Russo-Ukrainian War.
America
Their words
The United States of America didn’t want the Soviet Union to collapse and disintegrate. They didn’t want that at the start of the Cold War in 1948. We now have the strategic documents. They were concerned about that, they didn’t want to do that. And certainly they didn’t want to do that in the year 1991.
Show the whole quote
youtube.com
22 September 2023
Economic historian writing on the Industrial Revolution, the Great Divergence and the origins of modern growth.
For anyone interested I have a surfeit of codes to B***S** that I’d be happy to hand out. I’m also dkedrosky Over There, incidentally. Related
Nothing matches. Show everything
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.
Got it
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.
Got it