Related posts
Kun Chen
GitHub
axi — Design principles for agent ergonomics. Higher accuracy with lower token cost than both MCP and regular CLI.
MCP ergonomics accuracy
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.
Sources
All
Writing
GitHub Mastodon x.com Recommends Blog Bluesky Korrents Site Papers
Top people
Peter Steinberger
Eugene Yan
Kaspars Dambis
Kent C. Dodds
Dax Raad
Harper Reed
Mario Zechner
Tim Bray
Armin Ronacher
Tomasz Tunguz
Jason Fried
Karri Saarinen
Showing
Profile →
Show everything
Hiding
Show them again
Show them again
Further back ↓
Hiding
Show them again
21 September
Software engineer and educator; creator of Testing Library and of the EpicWeb.dev and EpicReact.dev courses.
20 September
Canadian software developer and writer, co-editor of the XML and Atom specifications and formerly of Sun Microsystems, Google and AWS. Has written the blog ongoing since 2003.
The #Fujifilm bandwagon is diverse: https://petapixel.com/2026/09/19/women-and-younger-photographers-are-behind-fujifilms-meteoric-rise/ Seems pretty obvious why: The cameras are smaller, lighter, and have really good ergonomics. Related
18 September
Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.
gog has an mcp server now! gogcli.sh
Quoting @EdgeDimi Someone tell him to not over fixate while king @steipete has solved gws with gog cli months back. MCP Related
Creator of Flask and Jinja. Writes about software at lucumr.pocoo.org.
I wonder if at this point there couldn't be a very of MCP that is literally codemode + openapi + RAG for openapi docs instead. The reference Radius skill is just OpenAPI and it works so well. MCP Related
17 September
Venture capitalist and founder of Theory Ventures, previously a partner at Redpoint. Writes a near-daily blog on startups, SaaS metrics, data and AI.
The better the harness, the better the business. Berkeley published a study this week showing harnesses, the systems that control AI agents, set the price of an answer. The right harness cuts the cost of the same result by 71% without a loss of accuracy. Related
16 September
Software engineer and educator; creator of Testing Library and of the EpicWeb.dev and EpicReact.dev courses.
10 September
Latvian full-stack WordPress developer and course creator at WPElevator; blogs since 2007 about the open web, electronics, home automation and sustainable living.
Today I learned that @OpenAIDevs MCP client https://t.co/nhRPF6KVEf lists private_key_jwt for the token endpoint auth while the CIMD endpoint is actually public (auth=none). So your MCP OAuth must be able to skip private_key_jwt, if unsupported. MCP Related
7 September
Latvian full-stack WordPress developer and course creator at WPElevator; blogs since 2007 about the open web, electronics, home automation and sustainable living.
Pretty cool to see your WordPress site as a connector in the Claude mobile app. It is a streamable-http MCP server by Agent Pilot plugin combined with OAuth Pilot for seamless auth. Also works with the official MCP-adapter feature plugin. MCP Anthropic Related
4 September
Latvian full-stack WordPress developer and course creator at WPElevator; blogs since 2007 about the open web, electronics, home automation and sustainable living.
With Agent Pilot you can create and manage agent skills in WordPress (just like blog posts) and publish them as standard Agent Plugins. Now with OAuth Pilot you get one-click authentication for all the MCP clients (Claude, ChatGPT, etc). No more application passwords! MCP Anthropic Related
3 September
Co-founder and CEO of 37signals, makers of Basecamp and HEY; co-author of Rework, Remote and It Does Not Have to Be Crazy at Work.
Goodbye per-seat pricing. Per-user pricing has always rubbed me the wrong way. And in this agentic age, it feels downright antique. For the vast majority of the time Basecamp has been on offer, we never charged per-user. A few years ago we experimented with one pay-per-user plan, and that experiment just came to an end. And it couldn’t come at a better time. With the Basecamp CLI (and soon MCP, too), you can bring your agents to Basecamp as users too. Charging you for individual agents feels just as wrong as charging you for individual people. So today we have brand new pricing plans with NO… basecamp.com
MCP Related
Co-founder and CEO of Linear; previously principal designer at Airbnb, where he led the Design Language System, and founding designer at Coinbase.
Thanks @jasonlk! Lot to do still but: 1) @linear is used by pretty much by all major labs/ai companies out there 2) our MCP traffic grows 50% MoM 3) we have the most agent integrations and active usage than any platform like this (3rd party, in-house agents) 4) our AI revenue (loops, coding sessions) has grown about 500% per quarter 5) we are closing several public companies/enterprises each quarter to help them coordinate their agent work Quoting @HarryStebbings The Bull Case for Linear Being a $100BN Company: "Linear is the clear winner. They have built an agentic product first that allows us to build 100x more software, and that means 100x more features than ever before. Humans cannot keep up with it, and humans still have to work with agents. If every h… MCP Related
Builds developer tools — SST, and now OpenCode at Anomaly. Posts constantly on x.com and writes almost never; the blog stopped in 2021.
Their words
i analyzed a weeks worth of data via honeycomb + planetscale mcp and opencode2's codemode
Show the whole quote
x.com
Their words
i analyzed a weeks worth of data via honeycomb + planetscale mcp and opencode2's codemode
Show the whole quote
x.com
2 September
Reviews sports technology at DC Rainmaker — watches, power meters and bike computers — in exhaustive detail, having tested them himself.
29 August
Co-founder and CEO of Stripe and co-founder of the Arc Institute. Keeps a personal site of reading lists, open questions and notes on scientific progress and how research is funded.
Between wallets for agents with @link (and @privy), MPP, Tempo, MCP, Stripe CLI, Agentic Commerce Suite, sandboxes, OpenRouter, Metronome/metered billing, Radar and distillation/token fraud, it turns out that "the economic infrastructure for AI" implicates a lot. Pretty much every layer of the Stripe stack is changing, and it’s a very good time to join if you want to build high-scale software that facilitates the practical deployment of this new intelligence. MCP Related
28 August
Developer and podcaster; created Instapaper and Overcast, co-founded Tumblr, and co-hosts the Accidental Tech Podcast.
RE: https://social.tupo.space/@joshua/117174153454890194 My current AI-code policy is that I will always use the best model I can access, as long as it's practically able to do the job. Right now, as far as I know, that's Fable. Quality and accuracy matter FAR more to me than volume or speed of output. And I feel that I owe it to my customers — and myself — to use the best tools at my disposal. Cost may be a factor to others, so no judgment. This is just my policy for myself. Related
24 August
Scottish software developer on the Statamic core team; runs a one-person business maintaining Statamic addons such as Runway and writes at duncanmcclean.com.
22 August
Technologist and entrepreneur; former CTO of Threadless and chief technology officer of the 2012 Obama re-election campaign.
16 August
Principal engineer at Cloudflare as of 2026, on agents and developer tooling. Streams TypeScript, OCaml and Neovim on Twitch, and wrote the better-result library after writing the same Result type about a hundred times.
8 August
Brazilian-American staff software engineer working on platforms, AI and developer productivity. Writes about engineering and his setup at ivansantos.me.
Friendly tip for anyone vibe-coding a side project: instrument it. All of it — traces, metrics, logs, profiles. Send it to @grafana, hook up their MCP, and let the agent debug with real data instead of guessing. MCP Related
7 August
Latvian full-stack WordPress developer and course creator at WPElevator; blogs since 2007 about the open web, electronics, home automation and sustainable living.
There is now a standard for bundling agent skills and MCP configurations as portable plugins (zip files) https://t.co/eAxXQQXWZg This is amazing for self-hosting your AI tools and not needing to publish to individual vendor marketplaces. MCP Related
4 August
Technologist and entrepreneur; former CTO of Threadless and chief technology officer of the 2012 Obama re-election campaign.
31 July
Co-founder of Modem and a founding engineer at Sentry, where he went on to be VP of Engineering. Co-author of Third-party JavaScript, and co-host of the State of Agentic Coding podcast with Armin Ronacher.
It's becoming normal practice to plug your coding agent into tools like Slack and helpdesk software to find customer insights. Turns out it's super inefficient, because you're just fetching and smashing raw strings into your context repeatedly. So we released a new MCP server that solves that. MCP Related
30 July
Web infrastructure engineer and standards editor; chaired the IETF HTTP working group and co-authored core HTTP and Atom specifications.
28 July
Web developer and writer; an early GitHub employee, author of speaking.io and of widely read essays on startups and product.
"Make the strongest possible case that my worst investment was actually my best one, and that I'm the only person who can see it." Been having a lot of fun with our new MCP server in Signed: signed.com
MCP Related
26 July
Co-founder of NVIDIA and, as of 2026, its chief executive; the company designs the GPUs most large AI models are trained on.
13 July
Professor of psychology at UCLA, where he studies human memory, attention and cognitive ageing, and author of Better with Age: The Psychology of Successful Aging.
Their words
And sometimes confidence, high confidence doesn't necessarily mean high accuracy. And I think part of the reason we're fooled is usually, you know, the more you see something, the better you'll remember it, just like the Apple logo. But that's not always the case.
Show the whole quote
youtube.com
2 July
Founder and editor-in-chief of MacStories, writing about Apple software, iPad workflows and automation since 2009. He co-hosts the AppStories podcast.
Safari’s New MCP Server Is Great for Agents Saron Yitbarek, writing on the WebKit blog: In Safari Technology Preview 247, we’re introducing the Safari MCP server — a Model Context Protocol server for web developers that makes your web development and debugging wo…
MCP Related
29 June
Writer and teacher on productivity and personal knowledge management. Author of Building a Second Brain and founder of Forte Labs, which runs the course of the same name.
Their words
This is why I recommend ignoring the vast web of custom and “community-built” MCP servers you can find out there, and focusing your attention on the two safer bets instead
Show the whole quote
fortelabs.com
21 June
Freelance climate and energy analyst in Oslo, writing on Europe, the US and Australia; worked in the Australian renewables industry before that.
LLMs energy
Their words
Generative AI has no internal, designed momentum towards truth and accuracy (beyond the absurdly diminishing returns of energy-hungry multi-layered LLMs), but a person or an institution can (and should).
Show the whole quote
ketanjoshi.co
17 June
Founder and CEO of Wolfram Research, creator of Mathematica and Wolfram|Alpha, and author of A New Kind of Science.
Another new thing delivered with Version 15: click a button to give Wolfram superpowers to your AI system! Immediately connect Claude, Codex, etc. to your local Wolfram|One, Mathematica, etc. via MCP... MCP Anthropic Related
3 June
Engineer and teacher; wrote Kubernetes the Hard Way, was a distinguished engineer at Google Cloud, and retired from full-time work in 2023.
MCP
Their words
So I'm looking at this like guys the fundamentals of this isn't like everything is going to change because of MCP. What the hell? A whole conference guys? This is just API design.
Show the whole quote
youtube.com
25 May
Swedish programmer with degrees in engineering and psychology, author of Your Code as a Crime Scene and founder of CodeScene.
I still meet people convinced that AI coding tools will soon reach a point where code quality, design, and even architecture are "solved". So I ran a small ad-hoc experiment. I’ve been working on a CLI tool and let agents plan and implement a first functionally correct version. I provided strict instructions around testing strategy, workflows, and implementation constraints. But I deliberately removed the @codescene MCP and the safeguards I normally rely on. Unsurprisingly, the resulting code suffered from a ton of problems. It would have been a shaky foundation to continue building on. How s… MCP Related
29 April
Canadian full-stack web developer who makes JavaScript and CSS video courses and co-hosts the Syntax podcast.
7 April
Scientist and writer on quantum computing, memory systems and metascience; co-wrote the standard quantum computation textbook and wrote Reinventing Discovery.
Their words
And so, you have what seem like three very different disconnected phenomena all being explained by this one set of ideas.
Show the whole quote
youtube.com
12 February
Software developer and entrepreneur; co-founder of Heroku, author of The Twelve-Factor App, and a researcher at Ink & Switch.
Two weeks of real-world use on Firehose, my email triage prototype. • 572 emails automatically labeled • 77% coverage (confident labels) • 98.2% accuracy on confident ✨ Related
Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.
MCP
Their words
I think the main beauty is, is that models are really good at calling Unix commands. So if you just add another CLI, that's just another Unix command in the end. And MCP is… That has to be added in training. That's not a very natural thing for the model. It requires a very specific syntax. And the biggest thing, it's not composable.
Show the whole quote
youtube.com
15 January
American senior staff engineer working on developer and user experience and open source; writes at adamdehaven.com.
AI assistants are getting better, but they still need context to work well with real tools and systems. The Model Context Protocol (MCP) is one way to provide that missing context. I wrote a guide on building and deploying your own MCP server: adamdehaven.com
MCP Related
1 January
Writer on habits and decision-making; author of Atomic Habits and the 3-2-1 newsletter, and publisher of long-running book recommendation lists.
31 December 2025
Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.
23 November 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.
From one piece
Product Evals in Three Simple Steps
2 beliefs, in the piece's order there
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.
11 September 2025
Machine learning engineer and consultant focused on RAG and retrieval systems. He writes about applied AI engineering at jxnl.co and is the author of the instructor library.
25 August 2025
Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.
22 August 2025
Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.
15 August 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.
19 July 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.
4 July 2025
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.
3 July 2025
Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.
21 May 2025
Founder of OpenStreetMap, the collaborative map of the world; later worked on mapping at Microsoft and Telenav.
I've been avoiding looking at MCP because it just smelled wrong. And yes, it's just XML-RPC but it's JSON. It smells like... SUN SPARCStation and 1999. MCP Related
4 May 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.
18 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.
Interesting paper from Google that challenges a core assumption in translation evaluation—a single metric can measure both accuracy & naturalness. They found that the best systems had neural metrics that did not correlate with human preferences. arxiv.org
Google Related
12 December 2024
Creator of Claude Code at Anthropic.
25 May 2024
Neuroscientist at UC Davis; studies memory and wrote Why We Remember.
Their words
And from what I understand, the research actually shows that they just produce what people want to hear, not necessarily the information that is being looked for.
Show the whole quote
youtube.com
1 January 2024
Professor of Cognitive and Computational Neuroscience at the University of Sussex, co-director of the Sussex Centre for Consciousness Science, and author of Being You: A New Science of Consciousness.
Nothing matches. Show everything
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.
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