Related posts

Dutch bootstrapper who builds and runs their internet startups alone — Nomads.com, Remote OK, Hoodmaps, Photo AI and Interior AI — and has written about it at levels.io since 2013. Posts as @levelsio.

• You're right, it was an elementary school not a military base. I'm sorry for the confusion. Would you like to learn more about elementary schools?
  Quoting@InsiderWN#BREAKING: Pentagon blames flawed intel and AI for strike that killed at least 123 Iranian children.

  Related

Creator of Ruby on Rails, CTO of 37signals, and creator of Omarchy.

• Lose the attitude, embrace optimism. Doctor's orders!
  Quoting@NTFabianoRepetitive negative thinking is linked to Alzheimer’s protein buildup in the brain.

  Related

Psychiatrist and clinical assistant professor at Case Western Reserve University. Writes Psychiatry at the Margins on the philosophical and scientific arguments inside psychiatry and the psy-sciences.

• Maybe Don’t Ask Your Doctor if Zoloft Is Right for You

  On imperfect tools

  Related

Marketing author and daily blogger; founder of the altMBA and the Akimbo workshops, and author of books including Purple Cow and This Is Marketing.

• Disconcerting genre shift

  If you sit down to watch a documentary and realize, about ten minutes in, that it’s actually a feature film, everything about it feels off until you shift into a different mode. Walk into a new doctor’s office, and it m…

  Related

CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.

• Looks like today may be a record day for token volume % of open models on Vercel AI Gateway: 🟦 Open 78.4% 🟨 Closed 21.6% While spend 💲 usually tells a different story, #3 and #4 today are Moonshot AI & DeepSeek. Adding Z⁠.ai, their combined spend surpasses OpenAI (#2). (Do note that's the spend for inference of the model across providers (mostly in the US), not revenue going directly to the open weight labs.)

  OpenAIRelated

British designer and technologist; co-founder of the design studio BERG, which made Little Printer, and writer of the blog Interconnected.

• I ran my second marathon last weekend but my write-up went a bit weird, sorry

  interconnected.org

  Related

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.

• and all it took was to add a proper extension system to claude code (sorry thariq, could not resist :D)
  Quoting@trq212We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config.

  AnthropicRelated

Creator of Ruby on Rails, CTO of 37signals, and creator of Omarchy.

• Great to welcome @OrcaRouter as a Distinguished Patron with a $150,000 donation to the Strategic Token Reserves for Omarchy! We're going to put their new OrcaCyber Zero 1.0 model to great use with our security and kernel work 🤘

  omarchy.org

  OmarchyRelated

Builds developer tools — SST, and now OpenCode at Anomaly. Posts constantly on x.com and writes almost never; the blog stopped in 2021.

• i've been really impressed with everything you've been saying and doing oh wait sorry confused you with someone else

  Related

Belgian engineering lead, Microsoft MVP and public speaker. Creator of Front Matter, a headless CMS extension for Visual Studio Code.

• doctor — Doctor - Maintain your documentation on SharePoint without pain.

  documentationRelated

Writes Nintil, long researched essays on metascience, biology, economics and whatever he has decided to read the literature on.

• Therapy is like dating: how to know if it's working

  If you have an injury or feel very ill most people don't bother thinking which specific hospital to visit or what doctor to see. The broad assumption is that an M.D. is an M.D., they are all well trained to deal with mo…

  PsychotherapyRelated

Physicist and science communicator. Writes Backreaction and makes videos explaining new physics and astronomy results, frequently to argue that the headline about them overstates the case.

• Woke up this morning with what is clearly an eye infection. Not good. Got the kids on the way to school. 7:30 I book an online appointment with a doctor. I send two photos. 7:35 I have phone chat with the doctor. 7:38 I have an electronic prescription for antibiotic drops. 7:59 I am standing in front of the pharmacy which opens at 8:00 8:15 back home, dripping my eye 9:00 the infection has visibly pretty much cleared out I am actually impressed by how flawlessly this all worked. I was fully prepared it'd eat up an entire day.

  Related

Writes The Pragmatic Engineer, the software-engineering newsletter, and wrote The Software Engineer's Guidebook. Formerly an engineering manager at Uber, and at Microsoft/Skype and Skyscanner before that.

• Here's what OpenAI's agentic software factory looks like, today. It's surely not token efficient, but eg agents "babysitting" releases to prod is something new, and an interesting approach. Details:

  newsletter.pragmaticengineer.com

  OpenAIRelated

Novelist and critic, author of The Body Scout and Metallic Realms; writes the newsletter Counter Craft on fiction craft and the publishing industry.

• Sorry this is very embarrassing. Why write about a literature you haven't read at all? American novels have one of the strongest comedic traditions that runs from Mark Twain to Percival Everett. And if you don't Moby-Dick is hilarious you should probably try reading the book
  Quoting@alysdenbyThe Great Flatsby: why American novels aren’t funny 🇺🇸😐 ✍️ me in @spectator

  AmericaRelated

British open-standards and open-source technologist, formerly of the UK Government Digital Service and the W3C Advisory Committee. Blogs at shkspr.mobi, where he posts a book review most weeks.

• [RSS Club] Sorry for breaking your feed readers!

  You're part of the Groovy Gang because you're a member of RSS Club! These posts are only available on my RSS and Atom feed. This post is not available in the shops, on the web, via FTP, or anywhere else. So, yeah, sorry…

  Related

Mathematical physicist at UC Riverside. Wrote This Week's Finds in Mathematical Physics and now the Azimuth blog on mathematics, physics and environmental science.

• Imagine thinking you had a good 20 years ahead of you. You go to the doctor for an annual physical, she does some tests, then comes back with a long face and says "I'm sorry to say: you have just 2 months to live". That's what just happened here. While planets in the inner Solar System are believed to have orbits that are unstable in the long term, astrophysicists thought the outer planets could last ~100 billion years before being picked off by other stars flying past, and other effects. But recently, we've learned something that changes this story. As red giants lose their mass by puffing o…

  solarRelated

Sociologist at Duke University writing on markets, exchange and moral order, and on plain-text and data-visualisation tools for social science.

• Targeted flattery-spam/phishing aimed at harmless academics like me is leveling up! Book Club rubbish is so last month. Thanks, LLMs! I just got a highly elaborate six-paragraph one “from” Emily St John Mandel (of Station Eleven fame). The choice of author to impersonate is really quite clever. Like the book club spam, it’s trawling for somewhat vain people who are susceptible to flattery, which of course excludes academic authors [puts hand to ear] sorry I’m just getting an update

  LLMsRelated

Independent iOS developer and podcaster; co-hosts the Accidental Tech Podcast and Analog(ue), and makes the apps Callsheet, MaskerAid and Peek-a-View.

• There is so much goddamned extra chrome on the Device Hub. Snap judgement, but not a fan. (Yes, I’m behind on 27 stuff. I’m sorry.)

  Related

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.

• The industry accepts there are 10x engineers But it hasn’t yet accepted there are 10x engineering *prompters* IMO it’s a real thing - and I’m not talking software factory token maxxers

  Related

Moroccan senior frontend developer writing at smakosh.com; builds side projects and client work under Smakosh LLC.

• Token breakdown improved on the analytics page on @llmgateway

  Related

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.

• look at me. i'm a token seller now. (please give us money, i need it for more icecream)
  Quoting@mitsuhikoIf you want to play around with an early thing: you can now give us money and we give you tokens in return.

  Related

Former L8 engineer at Meta, Microsoft and Atlassian, now writing and building solo on agentic engineering. Writes Kun's Field Notes and posts a lot about AI coding agents on X.

• ok everyone, i took one for the team here's the data we all wanted to see - real token value of each LLM subscription, empirically measured through usage on my real subscriptions - supergrok heavy has now become the highest value at $12k worth of tokens (40x ROI) - the $200 plan from openai and anthropic roughly give the same amount of token value, $7k give or take - cursor ultra's ROI is the lowest among mainstream subscriptions, roughly half of OAI or Ant. for individual consumers i'm afraid this no longer makes sense to purchase this was done in a clean environment. i ran each provider acr…

  LLMsAnthropicRelated

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.

  MCPRelated

Founder of Farnam Street (fs.blog) and host of The Knowledge Project podcast. Writes and curates on decision-making, mental models and rational thinking.

• Patterns of unhappy people: - Need social approval - Are reliably unreliable - Feel sorry for themselves - Choose comfort over truth - Refuse to learn from others - Spend more then they make - Use chemicals to alter mood - Make everything about them - Resent the success of others - Confuse motion with progress - Confuse cynicism with intelligence - Promiscious with their attention - Always in love with their first idea - Are alwasy too smart to look stupid - Need to learn everything from mistakes - Build a life that looks better than it feels - Protect their potential by never testing it - St…

  Related

Management writer; co-author of In Search of Excellence (1982) and author of The Excellence Dividend.

• A Doctor Sued 700 Patients for Debts; 81 Were Arrested. Now He’s a Senator. https://t.co/rJLJXTPZyM via @NYTimes

  Related

Writer of the newsletter bookbear express, on psychology, relationships, non-attachment and taste; based in San Francisco.

• just realized replies to my substack posts to have been going to spam for, oh, about a year. SORRY IF YOU EMAILED ME 💔💔💔

  Related

Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.

• Interesting details in here about how OpenAI researchers are using coding agents I'd love to know what caused the huge uptick in token spend in mid-July, was that when Astra became available to employees?
  Quoting@kliu128Today we're releasing data on models accelerating research at OpenAI. Recursive self-improvement could be the most important contributor to AI capabilities over the next few years, but by default it will only be seen inside a few frontier AI labs. Being transparent is more urgent than ever, so we c…

  coding agentsOpenAIRelated

Economics professor at George Mason University and author of The Myth of the Rational Voter, Selfish Reasons to Have More Kids, The Case Against Education and Open Borders. Writes Bet On It.

• AMA: Start of the 2026 Academic Year

  Here’s the video for last week’s AMA. I cut out the first seven minutes where the orientation was wrong. Sorry, it won’t happen again.

  Related

Co-founder and CEO of OpenAI; previously president of Y Combinator.

• first, sorry for the messy rollout. second, when we screw up, we try to make it right. third, we should be able to begin broad rollout to API customers and chatgpt subscribers in the near future. as usual we will start with pro subscribers.
  Quoting@thsottiauxWe will give one banked reset for every day you don't have access to Astra on your paid ChatGPT plan, starting today. Team is moving mountains to give access as fast as we can. First one will land in ~ 3 hours. There is still time to create your account if you don't have one.

  OpenAIRelated

Venture capitalist and founder of Theory Ventures, previously a partner at Redpoint. Writes a near-daily blog on startups, SaaS metrics, data and AI.

• How large is Snowflake's AI revenue? Management lowered product gross margin guidance from 76% → 74% due to "fast-growing AI workloads." If GPU inference runs at ~25%–35% gross margins, that 200 bps compression implies ~$60M–$75M/quarter (~$240M–$300M ARR) in direct AI token consumption.

  Related

Writer and developer. He runs the Latent Space newsletter and podcast about AI engineering, and writes essays on software and careers at swyx.io.

• sorry for the radio silence folks - got sucked into extreme LLM psychosis. but i can confidently say we have crossed over into a new age of AI Engineering and we are never, ever, looking back. this isnt even EVERYTHING i did with Astra but i'll append more reports as I publish them on LS!
  Quoting@latentspacepodWe spent >20B tokens throwing @openai's Astra at every AI Engineering task we could think of, beyond cute Blender demos and fun games. https://t.co/QoW6YBybA4 Here's everything Astra can do, and do so at <$6 an hour (serious): - choose and train models - label data (both helping you label and then…

  LLMsRelated

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.

• One more for the night: emulate v0.11 – Shared Next.js/Nuxt adapter runtime with persistent GitHub App key state – Linear issues now expose priorityLabel – GitHub token inspection adds perms, repo access, expiry and status

  github.com

  Related

Chilean web engineer building web experiences since 2006; co-founder of Media Creators and writes at iolivares.com.

• Yesterday I worked for ~20hs with my agents using Cursor and Claude and when I moved to sleep time I turned on the "autonomous" skill to all my agents. Today, checking the work done, almost 40% was blocked because reasons and when I ask they say "Sorry, my work was left unfinished..." Weird... computation outage?

  AnthropicRelated

Writer and academic, author of The Cult of Smart and How Elites Ate the Social Justice Movement; writes a daily newsletter on politics, education and culture.

• Sorry to Bother You

  I had this friend - haven’t seen him in at least fifteen years, not for any reason other than that life happens and you drift - I had this friend and he was a recovering addict.

  AddictionRelated

Chilean web engineer building web experiences since 2006; co-founder of Media Creators and writes at iolivares.com.

• La suscripción de 5x viene rindiendo, pero no estoy seguro si con el cambio del -17.5% de sesión vaya a estar bien. Pensando en probar Codex, veo a todos disfrutando de esa fiesta. Estamos en un mundo donde estar Token Maxing con una suscripción dejó de ser suficiente, ahora necesito 3 (Claude, Cursor y al parecer también Codex). 💸

  English, from SpanishThe 5x subscription is paying off, but I'm not sure if with the change of the -17.5% session it will be okay. Thinking about trying Codex, I see everyone enjoying that party. We're in a world where Token Maxing with one subscription is no longer enough, now I need 3 (Claude, Cursor, and apparently Codex too). 💸

  AnthropicRelated

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.

  MCPRelated

Venture capitalist and founder of Theory Ventures, previously a partner at Redpoint. Writes a near-daily blog on startups, SaaS metrics, data and AI.

• Does the token supply chain also experience the bullwhip effect? Here's my explanation of this classic phenomenon and what it means for AI data centers.

  data centersRelated

Canadian cartoonist and writer: Dinosaur Comics, Marvel's The Unbeatable Squirrel Girl, and the choose-your-own-path books To Be or Not To Be and Romeo and/or Juliet.

• t-rex and the case of the zesty zeitgeist

  archive - contact - sexy exciting merchandise - search - about &larr; previousAugust 26th, 2026next August 26th, 2026: Sorry for the lack of a comic Monday! I was travelling last week - a vacation! IT WAS GREAT! I ate i…

  Related

Belgian engineering lead, Microsoft MVP and public speaker. Creator of Front Matter, a headless CMS extension for Visual Studio Code.

• doctor-sample — Sample project for Doctor

  Related

Software engineer and founder of Block Party; previously an engineer at Pinterest and Quora, and a co-founder of the non-profit Project Include and the tech diversity data project Where are the Numbers?

• i'm always so excited to see that there are new replies to my slack threads until i realize it's just claude (sorry claude)

  AnthropicRelated

British software developer at Laravel and creator of the Cachet open-source status page system. Podcaster; writes at james.brooks.page.

• I've updated https://t.co/jtxQc4wgek with some missing packages (whoops!): - laravel/doctor - laravel/folio - laravel/tinker - laravel/wayfinder If we're missing anything else, lemme know!

  Related

AI research engineer working on large language models. He writes the Ahead of AI newsletter and is the author of Build a Large Language Model (From Scratch).

• x.comA couple of days ago, I did a quick explainer on Claude’s new watermarking process and implementation. Since it’s such a popular topic and sparked such a lively discussion, I thought it might be interesting to go into a bit more detail when explaining how it works. So, instead of the usual text article, I recorded a little lecture on the topic (to change it up a bit from my usual articles). It ended up a bit longer than intended, but I hope it clarifies a lot of things: - Sampling the next token in an LLM and pseudorandom number generators - How watermarking relates to the regular LLM samplin…

  LLMsAnthropicRelated

• NewsletterHow Claude Watermarks AI-Generated Text

  A 48-minute video walkthrough of token sampling, watermark detection, and removal

  AnthropicRelated

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.

• Liam, 8; I got stung by a bee! *moans* Me: I’m sorry. Liam: Why do bees sting? Me: In defense of themselves or their hive. Liam: I was nowhere near a hive. Me: He might have made a mistake. You’re ten thousand times bigger than him and so maybe he was terrified. Liam, suddenly…

  Related

Indonesian software engineer, educator and engineering manager at Zero One Group; open-source enthusiast writing at ripandis.com.

• DeepSeek V4 Flash naik harga. Limit usage di OpenCode Go juga turun drastis. Untung masih ada 17 juta (17M) token per hari gratis. Mau? Daftar sini aja:

  English, from IndonesianDeepSeek V4 Flash price increased. Usage limit on OpenCode Go also dropped drastically. Luckily there are still 17 million (17M) tokens per day for free. Want some? Register here:

  s.id

  Related

AI research engineer working on large language models. He writes the Ahead of AI newsletter and is the author of Build a Large Language Model (From Scratch).

• A short illustration of how the Claude's watermarking is supposed to work (based on my read of their released materials). In general, when we are generating tokens, there can be multiple high-scoring tokens at certain next-word positions. Usually, we sample with top-k or top-p sampling so the highest-scoring token is most often selected (if we repeat the sampling many times), but other tokens may be selected as well. With watermarking, there is a key that says which of the (ideally equally) highest-scoring tokens to select. Or, more concretely, the secret key and previous token influence the…
  Quoting@AnthropicAIWe’ve written an FAQ to answer some of the questions we've received about watermarking. In summary: • We’re implementing watermarking to comply with the EU AI Act. Other major model developers have signed the same Code of Practice and will also be implementing watermarking; • Our watermarking metho…

  AnthropicRelated

AI research engineer working on large language models. He writes the Ahead of AI newsletter and is the author of Build a Large Language Model (From Scratch).

• Build a Reasoning Model (From Scratch) is now finally also available on Amazon! Thanks so much to everyone who preordered! One important note for readers in India: please avoid ordering through @amazon India (@amazonIN) for now since they are selling counterfeit black-and-white copies. The genuine book is printed in color this time and includes a code for registering the book on Manning’s website. If you are based in India, I recommend ordering directly from Manning. (If you received a counterfeit copy, please return it. I am very sorry about the hassle.) Unfortunately, these counterfeit sale…

  Related

Lawyer and everyday-carry gear reviewer who publishes scored knife, flashlight and multitool reviews at Everyday Commentary.

• Carry Q2 2026

  The app I used to write the blog recently changed. This looked like it went up on Saturday, but it didn’t. Sorry for the delay. It has been a very good summer weather wise. With only a handful of days over 95 or under 7…

  Related

Security researcher; built Report URI and Security Headers, and writes about web security in practice.

• Device Bound Session Credentials lands in Chrome on macOS

  Device Bound Session Credentials (DBSC) is Chrome's answer to session cookie theft, usually by InfoStealer malware. Instead of a cookie being a bearer token that works anywhere it's pasted, DBSC binds the session to a p…

  Related

Programmer and writer on computer architecture, performance, and software reliability. He has worked on CPU design at Centaur Technology and on software at Google and Microsoft, and writes long-form technical essays at danluu.com.

• How do programming languages impact token efficiency and correctness?

  danluu.com

  Related

Canadian full-stack web developer who makes JavaScript and CSS video courses and co-hosts the Syntax podcast.

• I bought $100 of Claude API credits for $8 on the Chinese black market It's an insane, well run industry — some losing $10 million per month to theft Join me as I go deep on the AI token underworld

  youtube.com

  AnthropicChinaRelated

Full-stack developer, creator of Tailwind CSS; writes at adamwathan.me and makes courses and screencasts for web developers.

• Feels like we’re about 6 months away from a token is a token is a token. Just gas at the gas station.

  Related

Founding member of OpenAI and former director of AI at Tesla; creator of nanoGPT and the term "vibe coding".

• We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested what Opus 5 would do if I gave it the first paragraph of the Lord of the Rings, a 1M token budget (~$10) and asked for three js render of it. Opus went off for ~2 hours and wrote 5500 lines of code that (procedurally) rendered the story. It's kind of janky but fun. But it's a bit mindboggling that the LLM has to place and orchestrate various polygon assets in (x,y,z) coordinates and write code that animates it all, and that it even does…

  LLMsRelated

Software design writer and chief scientist at Thoughtworks; wrote Refactoring and Patterns of Enterprise Application Architecture.

• The Economic Benefit of Refactoring

  Giles Edwards-Alexander does an experiment to see if decomposing a large function helps reduce token costs, suggesting that is may now be possible to measure the economic benefit of refactoring more

  Related

Software design writer and chief scientist at Thoughtworks; wrote Refactoring and Patterns of Enterprise Application Architecture.

• The Orchestrator's Tax

  Subagents get justified by time saved and parallel execution, but Rahul Garg explains that's not what matters most. Every token in the orchestrator's context is competing for its attention, and the real value of a subag…

  Related

Creator of Ruby on Rails, CTO of 37signals, and creator of Omarchy.

• I'm sorry, Dave

  Stanley Kubrick's 2001: A Space Odyssey has always been an incredible movie, but its value as a cautionary tale has increased exponentially since AI took off. The iconic scene with HAL 9000 refusing to open the pod-bay…

  Related

Founding member of OpenAI and former director of AI at Tesla; creator of nanoGPT and the term "vibe coding".

• One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and ofte…

  LLMsRelated

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.

• 👋 New blog post: "How coding agents read files – and how to write for them" In it I explain how code optimized for agent-discovery can lead to major token savings on search + retrieval, even with frontier models like GPT-5.6 Sol Plus other important findings ⬇️

  coding agentsOpenAIRelated

Game designer and programmer, co-founder of id Software and co-creator of Doom, Quake and Wolfenstein 3D. Now runs Romero Games in Galway, Ireland.

• I’m so sorry for everyone at id Software affected by these layoffs. I know what it feels like to leave id while id goes on. It’s a strange and painful thing to step away from a place that holds so much of your work, friendships and history. The people at id have done a great job moving that legacy forward. DOOM, Quake, and Wolfenstein are not easy names to carry on, especially in today’s industry. The last few games showed real care, skill and respect for what those worlds mean to people. A note on digital preservation: id's history is critically important to the history of games. I’ve preser…

  Related

Writes Very Serious, a newsletter on politics, the economy and culture, and hosts the podcast of the same name.

• Europe Needs Air Conditioning

  Sorry if I'm boring any Europeans with this observation

  EuropeRelated

Systems and developer-tools engineer at Cloudflare as of 2026, on durable infrastructure for AI agents; worked on React and PartyKit before that. Writes at sunilpai.dev.

• never waste a token

  durable inference: resumable streams, crash recovery, and why the LLM request shouldn't die with your process.

  LLMsRelated

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.

• 🎨 hunk v0.15.0 is out: - supports git --color-moved - transparent backgrounds - color token fixes - more themes - Sapling support (it's a VCS from Meta) also now there's a website →

  hunk.dev

  Related

Technologist and entrepreneur; former CTO of Threadless and chief technology officer of the 2012 Obama re-election campaign.

• If you wanted to try out fable but are scared of blowing away your token budget do we have a skill for you! Its called Thrifty. It makes things cheaper. We built thrifty for claude code around a better split: strong model plans → cheap model executes → gate verifies.

  AnthropicRelated

Wall Street Journal bestselling author on marketing and writing, partner at MarketingProfs, and writer of the fortnightly Total Annarchy newsletter.

• Sorry for Ghosting: Where I’ve Been (Pssst New Book!)

  Ann Handley is back with a big announcement...her new book coming in 2027! She shares a peek into the writing process.

  Related

American front-end engineer and design-systems specialist; built the Pantsuit design system for Hillary for America and has worked at Slack and IBM.

• My TARDIS is Doctor approved 😌 I really should go to more cons 🤔
  Quoting@thatgirlbamz.bsky.socialId like to see all my BLACK folks who love to cosplay 👀. I wanna see the fits 🥰

  Related

Self-taught home cook and food writer who has run the Smitten Kitchen recipe site since 2006; author of four cookbooks.

• chicken salad for celery enthusiasts

  I’m not sure if this is a sign of hitting a certain age — like a sudden interest in bird feeders (check, and please tell me about yours), or beekeeping (well, in the TikTok sense, not sorry), and animated conversations…

  Related

London-based front-end architect, web developer evangelist and cloud consultant; Microsoft MVP. Writes at praveen.science and answers on Stack Overflow.

• snyk-challenge-international-soccer — I completed it.

  CommitsFixed token. · Completed. · File created.

  Related

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.

• Mythos evals from XBOW and UK AISI: • UK AISI: Mythos completed a 32-step network attack (est. at ~20 hrs for experts) in 6/10 tries. First model to solve their e2e cyber ranges! • XBOW: "token-for-token, unprecedented precision" Read more: https://t.co/hD6G6DvALg,

  xbow.com

  Related

Programmer and writer on computer architecture, performance, and software reliability. He has worked on CPU design at Centaur Technology and on software at Google and Microsoft, and writes long-form technical essays at danluu.com.

• What do people like for token-intensive workflows for personal projects? With a semi-autonomous workflow, I can exhaust a week's quota on the $200/mo codex plan in ~10 minutes of my time. If I'm in the loop, I get ~10x(?) the productivity per token, but it's time inefficient and

  Related

Software engineer, Wikipedia editor and crypto critic; writes Citation Needed and runs Web3 is Going Just Great.

• President Trump’s $TRUMP memecoin is preparing to launch a “Coin Club” membership scheme

  The website promises "elite and extraordinary experiences" as part of the newest scheme to revive a token that’s down 97% from its peak and still falling.

  Related

Founder and CEO of the search engine DuckDuckGo, and co-author of the books Traction and Super Thinking.

• 🆕✍️ Start collecting an AI "token tax" now; figure out exactly what to do with the funds later

  gabrielweinberg.com

  Related

Writer and consultant on formal methods and software correctness; author of Practical TLA+ and Logic for Programmers.

• A sufficiently comprehensive spec is not (necessarily) code

  Sorry for missing last week! Was sick and then busy. This week I want to cover a pet peeve of mine, best seen in this comic: A "comprehensive and precise spec" is not necessarily code. A specification corresponds to a s…

  Related

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.

• State of Agentic Coding #5 with @mitsuhiko.at is live. In this episode: - death of the IDE premature? - what's with all the bugs - will future models fix yesterday's AI code? - token abuse, slowing down, and more! YT: www.youtube.com/watch?v=qCpY... Spotify:

  open.spotify.com

  Related

Hosts the Lex Fridman Podcast — long, unhurried conversations with scientists, engineers and public figures. Several of the interviews quoted elsewhere on this site are episodes of it.

• This life is fucking amazing. I'm so grateful to be alive, with all of you on this miracle of a planet. Oh and I'm sorry if I fuck things up sometimes. I'm a flawed human. But I promise to do whatever I can to try to add some more understanding and love to this world. After the world leader convos I get attacked intensely by all sides, and many disparate online communities. It has led to some really low points for me mentally. But I don't matter. I'm listening. I'll do better. And I'll try to find the strength to do more of them, always with rigor and backbone, seeking to truly understand. An…

  Related

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…

  LLMsRelated

Hosts the Lex Fridman Podcast — long, unhurried conversations with scientists, engineers and public figures. Several of the interviews quoted elsewhere on this site are episodes of it.

• It was an honor to hang out with Jensen Huang, CEO of @nvidia, and do a long-form podcast with him. Really fun & fascinating technical deep-dive conversation on & off the mic. One of the most brilliant & thoughtful human beings I've ever met. NVIDIA is the most valuable company in the world by market cap and is the engine powering the AI revolution. Podcast probably out tomorrow (Monday) unless I get stuck in too many interesting conversations while running around in SF ;-) PS: I haven't checked my messages in days. Sorry for slow replies 🙏 Trying to stay deeply focused at in overwhelmingly…

  Related

American front-end engineer and design-systems specialist; built the Pantsuit design system for Hillary for America and has worked at Slack and IBM.

• I’ve gotten really good at advocating for myself and will not hesitate to fire a doctor if I feel dismissed. It’s time-consuming, exhausting, and infuriating, but can also be life-saving.
  Quoting@chronicillness.bsky.socialThis is criminal. This is why medical gaslighting is deadly. Maybe just believe women for once.

  Related

Computer performance engineer working on datacenter performance at OpenAI, previously Netflix and Sun/Joyent. Author of Systems Performance and BPF Performance Tools, and creator of flame graphs.

• Huge news for Doctor Who fans: DMP 1 & 3 found!

  bbc.com

  Related

Independent game developer, creator of the colony simulation RimWorld and author of Designing Games: A Guide to Engineering Experiences. Previously worked on BioShock Infinite.

• Why do people say AI "just" predicts the next token as though this is somehow simpler than thinking? If you can predict what someone will say, you must be tracing the same processes they used to generate those words. You must recreate their thought process. You must think.

  Related

Pen name of the Canadian-American writer behind mrmoneymustache.com, a blog on frugality, early retirement and index-fund investing that has run since 2011.

• Health Insurance: I'm still really happy with what I've been doing since since 2020: - Direct primary care (DPC) physician subscription - Sedera Health Sharing (alternative to insurance with a $5k annual max out of pocket type of setup) https://t.co/RB2oXA82eL Total monthly cost for me at 51 is about $400. And no copays for doctor visits! Cautions: works best for people without existing chronic expenses. Also check the ACA marketplace including subsidies which can be very affordable in some cases.
  Quoting@LancerShull@mrmoneymustache Wondering what your latest take is on health insurance? The marketplace plan I have more than doubled after an increase in income. Thanks for sharing your TRT experience. 👍💪☕

  Related

Semiconductor analyst; writes Fabricated Knowledge on the chip industry and the companies in it.

• Software Follow Up

  Let's refine the thesis. Sorry guys, the net cope means I'm probably going to be right.

  Related

Organizational psychologist and professor at the Wharton School. Author of Give and Take, Originals, Think Again and Hidden Potential, host of the Re:Thinking podcast, and writer of the GRANTED newsletter.

• Sorry, Marvel. The Greatest Superhero is Superman

  He's the most super... and the most human.

  Related

Organizational psychologist and professor at the Wharton School. Author of Give and Take, Originals, Think Again and Hidden Potential, host of the Re:Thinking podcast, and writer of the GRANTED newsletter.

• How to Pick a Job, Say No and Sorry, and Avoid AI Pitfalls

  My favorite reads of the past month

  Related

Computer performance engineer working on datacenter performance at OpenAI, previously Netflix and Sun/Joyent. Author of Systems Performance and BPF Performance Tools, and creator of flame graphs.

• My website is online as http at https://t.co/1cRpD64hyP, but I just broke the https links, sorry. If you delete the "s" then the links should still work.

  Related

Writer and engineer behind the blog Melting Asphalt, and co-author with Robin Hanson of The Elephant in the Brain.

• 2yo: it’s coldy outside weird that it can be sunny, cloudy, rainy, snowy, windy, stormy, even chilly… but not coldy sorry kid, English is hard

  Related

Co-founder and partner at Union Square Ventures in New York. Has written the AVC blog almost every day since 2003, on venture capital, startups, music and crypto.

• Hi Everyone. As many of you know, this account was taken over by a hacker on Tuesday and they ran an NFT scam on it. I feel terrible about that and am sorry for anyone who was scammed.

  Related

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.

• I got nerdsniped much harder than intended by Advent of Code and so here's a writeup of how to process a 20,000 element list in C++ template metaprogramming without blowing your compiler's stack, and also about manually compiling a regular expression into a compile-time state machine. Sorry but also not sorry:

  blog.nelhage.com

  Related

Pen name of the Canadian-American writer behind mrmoneymustache.com, a blog on frugality, early retirement and index-fund investing that has run since 2011.

• The Comfort Crisis

  As with many things in life these days, it all started with an episode of the Peter Attia podcast. In this edition, our nation’s most Badass Doctor was interviewing a guest I initially dismissed as not overly applicable…

  Related

Programmer; co-founded GitHub and was its CEO, and created the Mustache templating language and Resque.

• repl — Sometimes you need a REPL. Unmaintained, sorry.

  Related

Programmer known online as technomancy; author of Leiningen, the Clojure build tool, and a maintainer of the Fennel programming language.

• grenchman — Sorry about the name

  CommitsDon't send code to print the stack trace from the repl client.

  Related

Creator of the Zig programming language; president and lead developer of the Zig Software Foundation.

• Zig: January 2018 in Review

  One month (and a few days, sorry I'm late!) has passed since I did the December 2017 writeup, and so it's time for another month-in-review for my esteemed sponsors. LLVM 6 Readiness LLVM 6.0.0rc2 was just announced on t…

  Related