Related posts
aliases simplify bash
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 x.com Blog GitHub Mastodon Korrents
Top people
Nick Janetakis
Chris Tate
Tyler Cipriani
Mario Zechner
Guillermo Rauch
Tobias Lütke
Philip O'Toole
Eugene Yan
Andrej Karpathy
Dex Horthy
Simon Willison
Showing Profile →
Show everything
Hiding Show them again
Show them again
Further back ↓
Hiding Show them again
21 September
Co-founder and CEO of Shopify; long-time Linux user and Omarchy contributor.
MCP vs CLI for LLMs is the wrong discussion. People are debating at the wrong layer. Both work incredibly well as long as they are run through a repl like environment that can persist state. The funny thing about CLI is that CLI tools are usually accessed through BASH which happens to be a repl with persistent state (the file system), therefore cli works much better than mcp. But this isn't even close to being an intrinsic property of MCP. Just means that we need better harnesses. Right now the best repl for this are: - bash + fs - jupyter kernels - codemode type repls, usually quickjs LLMs u… LLMs MCP Related
14 September
Engineer at Vercel Labs as of 2026. Ships a steady stream of small developer tools — agent-browser, portless, json-render, native-sdk, the v0 SDK — and lists every one of them at ctate.dev.
Introducing Vercel Labs Tools for devs in the AI era agent-browser, skills, json-render, deepsec, fx, just-bash, portless, vgpu and more We experiment in public: ship early, learn from feedback, and keep working on what people find useful We've been shipping under the Labs name for a while. Now, Labs is an official team at Vercel focused on exploring new capabilities and primitives that change what developers and agents can do. Here's what to expect: → Labs products: maintained, supported, built to be relied on → Active experiments: moves fast, expect rough edges and breaking changes → Past e… vercel.com
Related
8 September
Freelance web developer and instructor. Author of the Dive Into Docker course; writes tutorials on Docker, deployment and development environments at nickjanetakis.com.
4 September
Engineer at Vercel Labs as of 2026. Ships a steady stream of small developer tools — agent-browser, portless, json-render, native-sdk, the v0 SDK — and lists every one of them at ctate.dev.
Now available: wterm for Svelte Give your Svelte app a <𝚃𝚎𝚛𝚖𝚒𝚗𝚊𝚕 /> Run it locally, over SSH or with just-bash Related
19 August
Software engineer working on distributed systems and databases; creator of rqlite, the distributed database built on SQLite.
11 August
Freelance web developer and instructor. Author of the Dive Into Docker course; writes tutorials on Docker, deployment and development environments at nickjanetakis.com.
25 June
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.
How do we eval if a model can find and exploit vulnerabilities? We discuss some benchmarks and the common pattern: • A sandboxed target within Docker containers • Inputs: code only (0-day), with patch (1-day scenario) • Tools such as bash, static analyzers, etc. • A grader to eval exploits or captured flags eugeneyan.com
benchmarks Related
30 April
Founding member of OpenAI and former director of AI at Tesla; creator of nanoGPT and the term "vibe coding".
Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights: The first theme I tried to push on is that LLMs are about a lot more than just speeding up what existed before (e.g. coding). Three examples of new horizons: 1. menugen: an app that can be fully engulfed by LLMs, with no classical code needed: input an image, output an image and an LLM can natively do the thing. 2. install .md skills instead of install .sh scripts. Why create a complex Software 1.0 bash script for e.g. installing a piece of software if you can write the installation out in words and say "just show this to… Quoting @stephzhan @karpathy and I are back! At @sequoia AI Ascent 2026. And a lot has changed. Last year, he coined “vibe coding”. This year, he’s never felt more behind as a programmer. The big shift: vibe coding raised the floor. Agentic engineering raises the ceiling. We talk about what it means to build seriousl… LLMs Related
24 April
Freelance web developer and instructor. Author of the Dive Into Docker course; writes tutorials on Docker, deployment and development environments at nickjanetakis.com.
17 April
Release engineering manager at the Wikimedia Foundation. Keeps a public log at tylercipriani.com of every book he reads, with a rating and notes.
Today's bash adventure, I never reach echo in this script: set -e (( X++ )) echo "X=$X" Why? Because (( X++ )) returns 0. And returning 0 from (( is a NON-zero exit code—an error. Because of course, how silly of me. Related
25 March
Austrian developer. Created the libGDX game framework, and more recently the pi coding agent, which moved with them to Earendil — Armin Ronacher's company — in April 2026. Writes at mariozechner.at.
9 March
Founder of HumanLayer; wrote 12-Factor Agents, on how to build AI agents that hold up in production.
31 December 2025
Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.
2 November 2025
Austrian developer. Created the libGDX game framework, and more recently the pi coding agent, which moved with them to Earendil — Armin Ronacher's company — in April 2026. Writes at mariozechner.at.
13 June 2024
CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.
2 March 2024
Release engineering manager at the Wikimedia Foundation. Keeps a public log at tylercipriani.com of every book he reads, with a rating and notes.
2 January 2024
CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.
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